Google Professional-Machine-Learning-Engineer Dumps

Vertex AI Pipelines is a service that allows you to create and run scalable and portable ML pipelines on Google Cloud. You can use Vertex AI Pipelines to add a component to divide the data into training and evaluation sets, and add another component for feature engineering. A component is a self-contained piece of code that performs a specific task in the pipeline. You can use the built-in components provided by Vertex AI Pipelines, or create your own custom components. By using Vertex AI Pipelines, you can orchestrate and automate your ML workflow, and track the provenance and lineage of your data and models. You can also enable autologging of metrics in the training component, which is a feature that automatically logs the metrics from your XGBoost model to Vertex AI Experiments. Vertex AI Experiments is a service that allows you to track, compare, and optimize your ML experiments on Google Cloud. You can use Vertex AI Experiments to monitor the training progress, visualize the metrics, and analyze the results of your model. You can also compare models using the artifacts lineage in Vertex ML Metadata. Vertex ML Metadata is a service that stores and manages the metadata of your ML artifacts, such as datasets, models, metrics, and executions. You can use Vertex ML Metadata to view the artifacts lineage, which is a graph that shows the relationships and dependencies among the artifacts. By using the artifacts lineage, you can compare the performance and quality of different models trained in different pipeline executions, and identify the best model for your use case. By using Vertex AI Pipelines, Vertex AI Experiments, and Vertex ML Metadata, you can execute the steps required for developing a training pipeline for a new XGBoost classification model based on tabular data stored in a BigQuery table. References:

• Vertex AI Pipelines documentation
• Vertex AI Experiments documentation
• Vertex ML Metadata documentation
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

 Reinforcement learning is a machine learning technique that enables an agent to learn from its own actions and feedback in an environment. Reinforcement learning does not require labeled data or explicit rules, but rather relies on trial and error and reward and punishment mechanisms to optimize the agent’s behavior and achieve a goal. Reinforcement learning can be used to solve complex and dynamic problems that involve sequential decision making and adaptation to changing situations1.

For the use case of creating an inventory prediction model for a large grocery retailer with stores in multiple regions, reinforcement learning is a suitable algorithm to use. This is because the problem involves multiple factors that affect the inventory demand, such as region, location, historical demand, and seasonal popularity, and the inventory manager needs to make optimal decisions on how much and when to order, store, and distribute the products. Reinforcement learning can help the inventory manager to learn from the new inventory data on a daily basis, and adjust the inventory policy accordingly. Reinforcement learning can also handle the uncertainty and variability of the inventory demand, and balance the trade-off between overstocking and understocking2.

The other options are not as suitable as option B, because they are not designed to handle sequential decision making and adaptation to changing situations. Option A, classification, is a machine learning technique that assigns a label to an input based on predefined categories. Classification can be used to predict the inventory demand for a single product or a single period, but it cannot optimize the inventory policy over multiple products and periods. Option C, recurrent neural networks (RNN), are a type of neural network that can process sequential data, such as text, speech, or time series. RNN can be used to model the temporal patterns and dependencies of the inventory demand, but they cannot learn from feedback and rewards. Option D, convolutional neural networks (CNN), are a type of neural network that can process spatial data, such as images, videos, or graphs. CNN can be used to extract features and patterns from the inventory data, but they cannot optimize the inventory policy over multiple actions and states. Therefore, option B, reinforcement learning, is the best answer for this question.

References:

• Reinforcement learning - Wikipedia
• Reinforcement Learning for Inventory Optimization

• Option A is incorrect because migrating your model to TensorFlow, and training it using Vertex AI Training, is not the easiest way to improve the model’s training time. TensorFlow is a framework that allows you to create and train ML models using Python or other languages. Vertex AI Training is a service that allows you to train and optimize ML models using built-in algorithms or custom containers. However, this option requires significant code changes, as TensorFlow and scikit-learn have different APIs and functionalities. Moreover, this option does not leverage the parallelism or the scalability of the cloud, as it only uses a single instance.
• Option B is incorrect because training your model in a distributed mode using multiple Compute Engine VMs, is not the most convenient way to improve the model’s training time. Compute Engine is a service that allows you to create and manage virtual machines that run on Google Cloud. You can use Compute Engine to run your scikit-learn model in a distributed mode, by using libraries such as Dask or Joblib. However, this option requires more effort and resources than option D, as it involves creating and configuring the VMs, installing and maintaining the libraries, and writing and running the distributed code.
• Option C is incorrect because training your model with DLVM images on Vertex AI, and ensuring that your code utilizes NumPy and SciPy internal methods whenever possible, is not the most effective way to improve the model’s training time. DLVM (Deep Learning Virtual Machine) images are preconfigured VM images that include popular ML frameworks and tools, such as TensorFlow, PyTorch, or scikit-learn1. You can use DLVM images on Vertex AI to train your scikit-learn model, by using a custom container. NumPy and SciPy are libraries that provide numerical and scientific computing functionalities for Python. You can use NumPy and SciPy internal methods to optimize your scikit-learn code, as they are faster and more efficient than pure Python code2. However, this option does not leverage the parallelism or the scalability of the cloud, as it only uses a single instance. Moreover, this option may not have a significant impact on the training time, as scikit-learn already relies on NumPy and SciPy for most of its operations3.
• Option D is correct because training your model using Vertex AI Training with GPUs, is the best way to improve the model’s training time. A GPU (Graphics Processing Unit) is a hardware accelerator that can perform parallel computations faster than a CPU (Central Processing Unit)4. Vertex AI Training is a service that allows you to train and optimize ML models using built-in algorithms or custom containers. You can use Vertex AI Training with GPUs to train your scikit-learn model, by using a custom container and specifying the accelerator type and count5. By using Vertex AI Training with GPUs, you can leverage the parallelism and the scalability of the cloud, and speed up the training process significantly, without changing your code.

References:

• DLVM images
• NumPy and SciPy
• scikit-learn dependencies
• GPU overview
• Vertex AI Training with GPUs
• [scikit-learn overview]
• [TensorFlow overview]
• [Compute Engine overview]
• [Dask overview]
• [Joblib overview]
• [Vertex AI Training overview]

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. Vertex AI AutoML Forecasting2 is a service that allows you to train and deploy custom time-series forecasting models for batch prediction. Vertex AI AutoML Forecasting simplifies the model development process by providing a graphical user interface and a no-code approach. You can use Vertex AI AutoML Forecasting to train a model by using your tabular data, and specify the target variable, the covariates, and the time variable. Vertex AI AutoML Forecasting automatically handles the feature engineering, model selection, and hyperparameter tuning. Therefore, option D is the best way to maximize the speed of model development and testing for the given use case. The other options are not relevant or optimal for this scenario. References:

• Professional ML Engineer Exam Guide
• Vertex AI AutoML Forecasting
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

• Explanation: TensorFlow Extended (TFX) is a platform for building end-to-end machine learning pipelines using TensorFlow. TFX provides a set of components that can be orchestrated using either the TFX SDK or Kubeflow Pipelines. TFX components can handle different aspects of the pipeline, such as data ingestion, data validation, data transformation, model training, model evaluation, model serving, and more. TFX components can also leverage other Google Cloud services, such as BigQuery, Dataflow, and Vertex AI.
• Why not A: Using the Kubeflow Pipelines SDK to implement the pipeline is a valid option, but using the BigQueryJobOp component to run the preprocessing script is not optimal. This would require writing and maintaining a separate SQL script for data transformation, which could introduce inconsistencies and errors. It would also make it harder to reuse the same preprocessing logic for both training and serving.
• Why not B: Using the Kubeflow Pipelines SDK to implement the pipeline is a valid option, but using the DataflowPythonJobOp component to preprocess the data is not optimal. This would require writing and maintaining a separate Python script for data transformation, which could introduce inconsistencies and errors. It would also make it harder to reuse the same preprocessing logic for both training and serving.
• Why not D: Using the TensorFlow Extended SDK to implement the pipeline is a valid option, but implementing the preprocessing steps as part of the input_fn of the model is not optimal. This would make the preprocessing logic tightly coupled with the model code, which could reduce modularity and flexibility. It would also make it harder to reuse the same preprocessing logic for both training and serving.

Vertex ML Metadata is a service that lets you track and manage the metadata produced by your ML workflows in a centralized way. It helps you have reproducible experiments by generating artifacts that represent the data, parameters, and metrics used or produced by your ML system. You can also analyze the lineage and performance of your ML artifacts using Vertex ML Metadata.

Some of the benefits of using Vertex ML Metadata are:

• It captures your ML system’s metadata as a graph, where artifacts and executions are nodes, and events are edges that link them as inputs or outputs.
• It allows you to create contexts to group sets of artifacts and executions together, such as experiments, runs, or projects.
• It supports querying and filtering the metadata using the Vertex AI SDK for Python or REST commands.
• It integrates with other Vertex AI services, such as Vertex AI Pipelines and Vertex AI Experiments, to automatically log metadata and artifacts.

The other options are not suitable for tracking and managing ML metadata in a centralized way.

• Option A: Storing your tf.logging data in BigQuery is not enough to capture the full metadata of your ML system, such as the artifacts and their lineage. BigQuery is a data warehouse service that is mainly used for analytics and reporting, not for metadata management.
• Option B: Managing all relational entities in the Hive Metastore is not a good solution for ML metadata, as it is designed for storing metadata of Hive tables and partitions, not for ML artifacts and executions. Hive Metastore is a component of the Apache Hive project, which is a data warehouse system for querying and analyzing large datasets stored in Hadoop.
• Option C: Storing all ML metadata in Google Cloud’s operations suite is not a feasible option, as it is a set of tools for monitoring, logging, tracing, and debugging your applications and infrastructure, not for ML metadata. Google Cloud’s operations suite does not provide the features and integrations that Vertex ML Metadata offers for ML workflows.

The test dataset is used to evaluate the performance of the ML model on unseen data. It should reflect the distribution of the data that the model will encounter in production. Therefore, if the retraining data includes new products, the test dataset should also be extended with images of those products to ensure that the model can generalize well to them. Keeping the original test dataset unchanged or replacing it entirely with images of the new products would not capture the diversity of the data that the model needs to handle. Updating the test dataset only when the evaluation metrics drop below a threshold would be reactive rather than proactive, and might result in poor user experience if the model fails to recognize the new products. References:

• Continuous evaluation documentation
• Preparing and using test sets

The best option for parametrizing the model training in Kubeflow Pipelines is to add a ContainerOp to the pipeline that spins a Dataproc cluster, runs a transformation, and then saves the transformed data in Cloud Storage. This option has the following advantages:

• It allows the data transformation to be performed as part of the Kubeflow Pipeline, which can ensure the consistency and reproducibility of the data processing and the model training. By adding a ContainerOp to the pipeline, you can define the parameters and the logic of the data transformation step, and integrate it with the other steps of the pipeline, such as the model training and evaluation.
• It leverages the scalability and performance of Dataproc, which is a fully managed service that runs Apache Spark and Apache Hadoop clusters on Google Cloud. By spinning a Dataproc cluster, you can run the PySpark transformation on the Parquet files stored in the Hive table, and take advantage of the parallelism and speed of Spark. Dataproc also supports various features and integrations, such as autoscaling, preemptible VMs, and connectors to other Google Cloud services, that can optimize the data processing and reduce the cost.
• It simplifies the data storage and access, as the transformed data is saved in Cloud Storage, which is a scalable, durable, and secure object storage service. By saving the transformed data in Cloud Storage, you can avoid the overhead and complexity of managing the data in the Hive table or the Parquet files. Moreover, you can easily access the transformed data from Cloud Storage, using various tools and frameworks, such as TensorFlow, BigQuery, or Vertex AI.

The other options are less optimal for the following reasons:

• Option A: Removing the data transformation step from the pipeline eliminates the parametrization of the model training, as the data processing and the model training are decoupled and independent. This option requires running the PySpark transformation separately from the Kubeflow Pipeline, which can introduce inconsistency and unreproducibility in the data processing and the model training. Moreover, this option requires managing the data in the Hive table or the Parquet files, which can be cumbersome and inefficient.
• Option B: Containerizing the PySpark transformation step, and adding it to the pipeline introduces additional complexity and overhead. This option requires creating and maintaining a Docker image that can run the PySpark transformation, which can be challenging and time-consuming. Moreover, this option requires running the PySpark transformation on a single container, which can be slow and inefficient, as it does not leverage the parallelism and performance of Spark.
• Option D: Deploying Apache Spark at a separate node pool in a Google Kubernetes Engine cluster, and adding a ContainerOp to the pipeline that invokes a corresponding transformation job for this Spark instance introduces additional complexity and cost. This option requires creating and managing a separate node pool in a Google Kubernetes Engine cluster, which is a fully managed service that runs Kubernetes clusters on Google Cloud. Moreover, this option requires deploying and running Apache Spark on the node pool, which can be tedious and costly, as it requires configuring and maintaining the Spark cluster, and paying for the node pool usage.

• Option A is incorrect because using AI Platform to run distributed training jobs with checkpoints does not reduce the compute costs, but rather increases them by using more resources and storing the checkpoints.
• Option B is incorrect because using AI Platform to run distributed training jobs without checkpoints may reduce the compute costs, but it also risks losing the progress of the training if the job fails or is interrupted.
• Option C is correct because migrating to training with Kubeflow on Google Kubernetes Engine, and using preemptible VMs with checkpoints can reduce the compute costs significantly by using cheaper and more scalable resources, while also preserving the state of the training with checkpoints.
• Option D is incorrect because using preemptible VMs without checkpoints may reduce the compute costs, but it also risks losing the training progress if the VMs are preempted.

References:

• Kubeflow on Google Cloud
• Using preemptible VMs and GPUs
• Saving and loading models

 A cloud-based backend system is a system that runs on a cloud platform and provides services or resources to other applications or users. A cloud-based backend system can be used to submit training jobs, which are tasks that involve training a machine learning model on a given dataset using a specific framework and configuration1

However, a cloud-based backend system can also have some drawbacks, such as:

• High maintenance: A cloud-based backend system may require a lot of administration and management, such as provisioning, scaling, monitoring, and troubleshooting the cloud resources and services. This can be time-consuming and costly, and may distract from the core business objectives2
• Low flexibility: A cloud-based backend system may not support all the frameworks and libraries that the data scientists need to use for their training jobs. This can limit the choices and capabilities of the data scientists, and affect the quality and performance of their models3
• Poor integration: A cloud-based backend system may not integrate well with other cloud services or tools that the data scientists need to use for their machine learning workflows, such as data processing, model deployment, or model monitoring. This can create compatibility and interoperability issues, and reduce the efficiency and productivity of the data scientists.

Therefore, it may be better to use a managed service instead of a cloud-based backend system to submit training jobs. A managed service is a service that is provided and operated by a third-party provider, and offers various benefits, such as:

• Low maintenance: A managed service handles the administration and management of the cloud resources and services, and abstracts away the complexity and details of the underlying infrastructure. This can save time and money, and allow the data scientists to focus on their core tasks2
• High flexibility: A managed service can support multiple frameworks and libraries that the data scientists need to use for their training jobs, and allow them to customize and configure their training environments and parameters. This can enhance the choices and capabilities of the data scientists, and improve the quality and performance of their models3
• Easy integration: A managed service can integrate seamlessly with other cloud services or tools that the data scientists need to use for their machine learning workflows, and provide a unified and consistent interface and experience. This can solve the compatibility and interoperability issues, and increase the efficiency and productivity of the data scientists.

One of the best options for using a managed service to submit training jobs is to use the AI Platform custom containers feature to receive training jobs using any framework. AI Platform is a Google Cloud service that provides a platform for building, deploying, and managing machine learning models. AI Platform supports various machine learning frameworks, such as TensorFlow, PyTorch, scikit-learn, and XGBoost, and provides various features, such as hyperparameter tuning, distributed training, online prediction, and model monitoring.

The AI Platform custom containers feature allows the data scientists to use any framework or library that they want for their training jobs, and package their training application and dependencies as a Docker container image. The data scientists can then submit their training jobs to AI Platform, and specify the container image and the training parameters. AI Platform will run the training jobs on the cloud infrastructure, and handle the scaling, logging, and monitoring of the training jobs. The data scientists can also use the AI Platform features to optimize, deploy, and manage their models.

The other options are not as suitable or feasible. Configuring Kubeflow to run on Google Kubernetes Engine and receive training jobs through TFJob is not ideal, as Kubeflow is mainly designed for TensorFlow-based training jobs, and does not support other frameworks or libraries. Creating a library of VM images on Compute Engine and publishing these images on a centralized repository is not optimal, as Compute Engine is a low-level service that requires a lot of administration and management, and does not provide the features and integrations of AI Platform. Setting up Slurm workload manager to receive jobs that can be scheduled to run on your cloud infrastructure is not relevant, as Slurm is a tool for managing and scheduling jobs on a cluster of nodes, and does not provide a managed service for training jobs.

References: 1: Cloud computing 2: Managed services 3: Machine learning frameworks : [Machine learning workflow] : [AI Platform overview] : [Custom containers for training]

 Vertex AI Workbench is an integrated development environment (IDE) that allows you to create and run Jupyter notebooks on Google Cloud. Vertex AI Pipelines is a service that allows you to create and manage machine learning workflows using Vertex AI components. To submit a Vertex AI Pipeline job from a Vertex AI Workbench instance, you need to have the appropriate permissions to access the Vertex AI resources. The Identity and Access Management (IAM) Vertex AI User role is a predefined role that grants the minimum permissions required to use Vertex AI services, such as creating and deploying models, endpoints, and pipelines. By assigning the Vertex AI User role to the Vertex AI Workbench instance, you can ensure that the instance has sufficient permissions to submit a Vertex AI Pipeline job. You can assign the role to the instance by using the Cloud Console, the gcloud command-line tool, or the Cloud IAM API. References: The answer can be verified from official Google Cloud documentation and resources related to Vertex AI Workbench, Vertex AI Pipelines, and IAM.

• Vertex AI Workbench | Google Cloud
• Vertex AI Pipelines | Google Cloud
• Vertex AI roles | Google Cloud
• Granting, changing, and revoking access to resources | Google Cloud

 Oversampling is a technique for dealing with imbalanced datasets, where the majority class dominates the minority class. It balances the distribution of classes by increasing the number of samples in the minority class. Oversampling can improve the performance of a classifier by reducing the bias towards the majority class and increasing the sensitivity to the minority class.

In this case, the dataset includes transactions, of which 1% are identified as fraudulent. This means that the fraudulent transactions are the minority class and the non-fraudulent transactions are the majority class. A random forest model trained on this dataset might have a low recall for the fraudulent transactions, meaning that it might miss many of them and fail to detect fraud. This could have a high cost for the bank and its customers.

One way to overcome this problem is to oversample the fraudulent transactions 10 times, meaning that each fraudulent transaction is duplicated 10 times in the training dataset. This would increase the proportion of fraudulent transactions from 1% to about 10%, making the dataset more balanced. This would also make the random forest model more aware of the patterns and features that distinguish fraudulent transactions from non-fraudulent ones, and thus improve its accuracy and recall for the minority class.

For more information about oversampling and other techniques for imbalanced data, see the following references:

• Random Oversampling and Undersampling for Imbalanced Classification
• Exploring Oversampling Techniques for Imbalanced Datasets

• Option A is incorrect because using AI Platform notebooks to perform a Lasso regression analysis on your model, which will eliminate features that do not provide a strong signal, is not a suitable way to determine which customer attribute has the most predictive power for each prediction served by the model. Lasso regression is a method of feature selection that applies a penalty to the coefficients of the linear model, and shrinks them to zero for irrelevant features1. However, this method assumes that the model is linear and additive, which may not be the case for a TensorFlow model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.
• Option B is incorrect because streaming prediction results to BigQuery, and using BigQuery’s CORR(X1, X2) function to calculate the Pearson correlation coefficient between each feature and the target variable, is not a valid way to determine which customer attribute has the most predictive power for each prediction served by the model. The Pearson correlation coefficient is a measure of the linear relationship between two variables, ranging from -1 to 12. However, this method does not account for the interactions between features or the non-linearity of the model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.
• Option C is correct because using the AI Explanations feature on AI Platform, and submitting each prediction request with the ‘explain’ keyword to retrieve feature attributions using the sampled Shapley method, is the best way to determine which customer attribute has the most predictive power for each prediction served by the model. AI Explanations is a service that allows you to get feature attributions for your deployed models on AI Platform3. Feature attributions are values that indicate how much each feature contributed to the prediction for a given instance4. The sampled Shapley method is a technique that uses the Shapley value, a game-theoretic concept, to measure the contribution of each feature to the prediction5. By using AI Explanations, you can get feature attributions for each prediction request, and identify the most important features for each customer.
• Option D is incorrect because using the What-If tool in Google Cloud to determine how your model will perform when individual features are excluded, and ranking the feature importance in order of those that caused the most significant performance drop when removed from the model, is not a practical way to determine which customer attribute has the most predictive power for each prediction served by the model. The What-If tool is a tool that allows you to visualize and analyze your ML models and datasets. However, this method requires manually editing or removing features for each instance, and observing the change in the prediction. This method is not scalable or efficient, and may not capture the interactions between features or the non-linearity of the model.

References:

• Lasso regression
• Pearson correlation coefficient
• AI Explanations overview
• Feature attributions
• Sampled Shapley method
• [What-If tool overview]

 The trace in the question shows that the training time is taking longer than expected. This is likely due to the input function not being optimized. To decrease training time in a cost-efficient way, the best option is to rewrite the input function using parallel reads, parallel processing, and prefetch. This will allow the model to process the data more efficiently and decrease training time. References:

• [Cloud TPU Performance Guide]
• [Data input pipeline performance guide]

BigQuery is a service that allows you to store and query large amounts of data in a scalable and cost-effective way. You can use BigQuery to ingest the Avro files from the Cloud Storage bucket and perform analytics on the structured data. Avro is a binary file format that can store complex data types and schemas. You can use the bq load command or the BigQuery API to load the Avro files into a BigQuery table. You can then use SQL queries to analyze the data and generate insights. Dataflow is a service that allows you to create and run scalable and portable data processing pipelines on Google Cloud. You can use Dataflow to create the features for your ML models, such as transforming, aggregating, and encoding the data. You can use the Apache Beam SDK to write your Dataflow pipeline code in Python or Java. You can also use the built-in transforms or custom transforms to apply the feature engineering logic to your data. Vertex AI Feature Store is a service that allows you to store and manage your ML features on Google Cloud. You can use Vertex AI Feature Store to host the features that your ML models use for online prediction. Online prediction is a type of prediction that provides low-latency responses to individual or small batches of input data. You can use the Vertex AI Feature Store API to write the features from your Dataflow pipeline to a feature store entity type. You can then use the Vertex AI Feature Store online serving API to read the features from the feature store and pass them to your ML models for online prediction. By using BigQuery, Dataflow, and Vertex AI Feature Store, you can configure a pipeline that performs analytics, creates features, and hosts the features that your ML models use for online prediction. References:

• BigQuery documentation
• Dataflow documentation
• Vertex AI Feature Store documentation
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

• Option A is incorrect because training local surrogate models to explain individual predictions is not a feature of Vertex Explainable AI, but rather a general technique for interpreting black-box models. Local surrogate models are simpler models that approximate the behavior of the original model around a specific input1.
• Option B is correct because configuring sampled Shapley explanations on Vertex Explainable AI is a way to explain the difference between the actual prediction and the average prediction for a given input. Sampled Shapley explanations are based on the Shapley value, which is a game-theoretic concept that measures how much each feature contributes to the prediction2. Vertex Explainable AI supports sampled Shapley explanations for tabular data, such as customer churn3.
• Option C is incorrect because configuring integrated gradients explanations on Vertex Explainable AI is not suitable for explaining the difference between the actual prediction and the average prediction for a given input. Integrated gradients explanations are based on the idea of computing the gradients of the prediction with respect to the input features along a path from a baseline input to the actual input4. Vertex Explainable AI supports integrated gradients explanations for image and text data, but not for tabular data3.
• Option D is incorrect because measuring the effect of each feature as the weight of the feature multiplied by the feature value is not a valid way to explain the difference between the actual prediction and the average prediction for a given input. This method assumes that the model is linear and additive, which is not the case for an ensemble of trees and neural networks. Moreover, this method does not account for the interactions between features or the non-linearity of the model5.

References:

• Local surrogate models
• Shapley value
• Vertex Explainable AI overview
• Integrated gradients
• Feature importance

The best option to serve the model while optimizing cost, user experience, and ease of management is to deploy the model to Vertex AI Prediction, which is a managed service that can scale up or down according to the demand and provide low latency and high availability. Vertex AI Prediction can also handle TensorFlow models natively, without requiring any additional steps or conversions. By using batch prediction, the model can process large volumes of data efficiently and periodically, without affecting the user experience. The data can be read from Cloud Bigtable, which is a scalable and performant NoSQL database that can store user data in a flexible schema. The predictions can then be pushed to Cloud SQL, which is a fully managed relational database that can store the predictions in a structured format and enable easy querying and analysis. This option also simplifies the management of the model and the data, as it leverages the existing Google Cloud services and does not require any additional infrastructure or code.

The other options are not optimal for the following reasons:

• A. Importing the model into BigQuery ML is not a good option, as it requires converting the TensorFlow model into a format that BigQuery ML can understand, which can introduce errors and reduce the performance. Moreover, BigQuery ML is not designed for serving real-time predictions, but rather for training and evaluating models using SQL queries. Reading and writing data from BigQuery and Cloud SQL can also incur additional costs and latency, as they are both relational databases that require schema definition and data transformation.
• C. Embedding the model in the mobile application is not a good option, as it increases the size and complexity of the application, and requires updating the application every time the model changes. Moreover, it exposes the model to the users, which can pose security and privacy risks, as well as potential misuse or abuse. Additionally, it does not leverage the benefits of the cloud, such as scalability, reliability, and performance.
• D. Embedding the model in the streaming Dataflow pipeline is not a good option, as it requires building and maintaining a custom pipeline that can handle the model inference and data processing. This can increase the development and operational costs and complexity, as well as the potential for errors and failures. Moreover, it does not take advantage of the batch prediction feature of Vertex AI Prediction, which can optimize the resource utilization and cost efficiency.

References:

• Professional ML Engineer Exam Guide
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate
• Google Cloud launches machine learning engineer certification
• Vertex AI Prediction documentation
• Cloud Bigtable documentation
• Cloud SQL documentation

 Sentiment analysis is the process of identifying and extracting the emotions, opinions, and attitudes expressed in a text or speech. Sentiment analysis can help businesses understand their customers’ feedback, satisfaction, and preferences. There are different approaches to building a sentiment analysis tool, depending on the input data and the output format. Some of the common approaches are:

• Extracting sentiment directly from the voice recordings: This approach involves using acoustic features, such as pitch, intensity, and prosody, to infer the sentiment of the speaker. This approach can capture the nuances and subtleties of the vocal expression, but it also requires a large and diverse dataset of labeled voice recordings, which may not be easily available or accessible. Moreover, this approach may not account for the semantic and contextual information of the speech, which can also affect the sentiment.
• Converting the speech to text and building a model based on the words: This approach involves using automatic speech recognition (ASR) to transcribe the voice recordings into text, and then using lexical features, such as word frequency, polarity, and valence, to infer the sentiment of the text. This approach can leverage the existing text-based sentiment analysis models and tools, but it also introduces some challenges, such as the accuracy and reliability of the ASR system, the ambiguity and variability of the natural language, and the loss of the acoustic information of the speech.
• Converting the speech to text and extracting sentiments based on the sentences: This approach involves using ASR to transcribe the voice recordings into text, and then using syntactic and semantic features, such as sentence structure, word order, and meaning, to infer the sentiment of the text. This approach can capture the higher-level and complex aspects of the natural language, such as negation, sarcasm, and irony, which can affect the sentiment. However, this approach also requires more sophisticated and advanced natural language processing techniques, such as parsing, dependency analysis, and semantic role labeling, which may not be readily available or easy to implement.
• Converting the speech to text and extracting sentiment using syntactical analysis: This approach involves using ASR to transcribe the voice recordings into text, and then using syntactical analysis, such as part-of-speech tagging, phrase chunking, and constituency parsing, to infer the sentiment of the text. This approach can identify the grammatical and structural elements of the natural language, such as nouns, verbs, adjectives, and clauses, which can indicate the sentiment. However, this approach may not account for the pragmatic and contextual information of the speech, such as the speaker’s intention, tone, and situation, which can also influence the sentiment.

For the use case of building a sentiment analysis tool that predicts customer sentiment from recorded phone conversations, the best approach is to convert the speech to text and extract sentiments based on the sentences. This approach can balance the trade-offs between the accuracy, complexity, and feasibility of the sentiment analysis tool, while ensuring that the gender, age, and cultural differences of the customers who called the contact center do not impact any stage of the model development pipeline and results. This approach can also handle different types and levels of sentiment, such as polarity (positive, negative, or neutral), intensity (strong or weak), and emotion (anger, joy, sadness, etc.). Therefore, converting the speech to text and extracting sentiments based on the sentences is the best approach for this use case.

TFRecords are a binary file format that can store large amounts of data efficiently. By converting the images to TFRecords and storing them in a Cloud Storage bucket, you can reduce the data size and improve the data transfer speed. You can then read the TFRecords by using the tf.data.TFRecordDataset function, which creates a dataset of tensors from the TFRecord files. This way, you can read images at scale during training while minimizing data I/O bottlenecks. References:

• TFRecord documentation
• tf.data.TFRecordDataset documentation
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

• Option A is incorrect because training a time-series model to predict the machines’ performance values, and configuring an alert if a machine’s actual performance values significantly differ from the predicted performance values, is not the best way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option assumes that the performance values follow a predictable pattern, which may not be the case for complex systems. Moreover, this option does not use any historical incident data, which may contain useful information for identifying failures. Furthermore, this option does not involve any model evaluation or validation, which are essential steps for ensuring the quality and reliability of the model.
• Option B is correct because implementing a simple heuristic (e.g., based on z-score) to label the machines’ historical performance data, and training a model to predict anomalies based on this labeled dataset, is a reasonable way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option uses a simple and fast method to label the historical performance data, which is necessary for supervised learning. A z-score is a measure of how many standard deviations a value is away from the mean of a distribution1. By using a z-score, we can label the performance values that are unusually high or low as anomalies, which may indicate failures. Then, we can train a model to learn the patterns of normal and anomalous performance values, and use it to predict anomalies on new data. We can also evaluate and validate the model using metrics such as precision, recall, or F1-score, and compare it with other models or methods.
• Option C is incorrect because developing a simple heuristic (e.g., based on z-score) to label the machines’ historical performance data, and testing this heuristic in a production environment, is not a safe way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option does not involve any model training or evaluation, which are essential steps for ensuring the quality and reliability of the solution. Moreover, this option does not test the heuristic on a separate dataset, such as a validation or test set, before deploying it to production, which may lead to errors or failures in the production environment.
• Option D is incorrect because hiring a team of qualified analysts to review and label the machines’ historical performance data, and training a model based on this manually labeled dataset, is not a feasible way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option may produce high-quality labels, but it is also costly, time-consuming, and prone to human errors or biases. Moreover, this option may not scale well with large or complex datasets, which may require more analysts or more time to label.

References:

• Z-score
• [Predictive maintenance]
• [Anomaly detection]
• [Time-series analysis]
• [Model evaluation]

 Labels are key-value pairs that you can attach to AI Platform resources such as jobs, models, and versions. Labels can help you organize your resources into descriptive categories that reflect your business needs. For example, you can use labels to indicate the owner, purpose, environment, or status of a resource. You can also use labels to filter the results when you list or monitor your resources on the Google Cloud Console or the Cloud SDK. Using labels can help you manage your resources in a clean and scalable way, without requiring separate projects or restrictive permissions.

References:

• Using labels to organize AI Platform resources
• Creating and managing labels

QUESTION 52

You are training a deep learning model for semantic image segmentation with reduced training time. While using a Deep Learning VM Image, you receive the following error: The resource 'projects/deeplearning-platforn/zones/europe-west4-c/acceleratorTypes/nvidia-tesla-k80' was not found. What should you do?

A. Ensure that you have GPU quota in the selected region.

B. Ensure that the required GPU is available in the selected region.

C. Ensure that you have preemptible GPU quota in the selected region.

D. Ensure that the selected GPU has enough GPU memory for the workload.

Answer: B

The error message indicates that the selected GPU type (nvidia-tesla-k80) is not available in the selected region (europe-west4-c). This can happen when the GPU type is not supported in the region, or when the GPU quota is exhausted in the region. To avoid this error, you should ensure that the required GPU is available in the selected region before creating a Deep Learning VM Image. You can use the following steps to check the GPU availability and quota:

• To check the GPU availability, you can use the gcloud compute accelerator-types list command with the --filter flag to specify the GPU type and the region. For example, to check the availability of nvidia-tesla-k80 in europe-west4-c, you can run:

gcloud compute accelerator-types list --filter="name=nvidia-tesla-k80 AND zone:europe-west4-c"

• If the command returns an empty result, it means that the GPU type is not supported in the region. You can either choose a different GPU type or a different region that supports the GPU type. You can use the same command without the --filter flag to list all the available GPU types and regions. For example, to list all the available GPU types in europe-west4-c, you can run:

gcloud compute accelerator-types list --filter="zone:europe-west4-c"

• To check the GPU quota, you can use the gcloud compute regions describe command with the --format flag to specify the region and the quota metric. For example, to check the quota for nvidia-tesla-k80 in europe-west4-c, you can run:

gcloud compute regions describe europe-west4-c --format="value(quotas.NVIDIA_K80_GPUS)"

• If the command returns a value of 0, it means that the GPU quota is exhausted in the region. You can either request more quota from Google Cloud or choose a different region that has enough quota for the GPU type.

References:

• Troubleshooting | Deep Learning VM Images | Google Cloud
• Checking GPU availability
• Checking GPU quota

The best option for deploying a custom tabular ML model to production for online predictions, and monitoring the feature distribution over time with minimal effort, using a model that was provided by the bank’s vendor, the training data is not available due to its sensitivity, and the model is packaged as a Vertex AI Model serving container which accepts a string as input for each prediction instance, is to upload the model to Vertex AI Model Registry and deploy the model to a Vertex AI endpoint, create a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective, and provide an instance schema. This option allows you to leverage the power and simplicity of Vertex AI to serve and monitor your model with minimal code and configuration. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can deploy a trained model to an online prediction endpoint, which can provide low-latency predictions for individual instances. Vertex AI can also provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance. A Vertex AI Model Registry is a resource that can store and manage your models on Vertex AI. A Vertex AI Model Registry can help you organize and track your models, and access various model information, such as model name, model description, and model labels. A Vertex AI Model serving container is a resource that can run your custom model code on Vertex AI. A Vertex AI Model serving container can help you package your model code and dependencies into a container image, and deploy the container image to an online prediction endpoint. A Vertex AI Model serving container can accept various input formats, such as JSON, CSV, or TFRecord. A string input format is a type of input format that accepts a string as input for each prediction instance. A string input format can help you encode your feature values into a single string, and separate them by commas. By uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, you can serve your model for online predictions with minimal code and configuration. You can use the Vertex AI API or the gcloud command-line tool to upload the model to Vertex AI Model Registry, and provide the model name, model description, and model labels. You can also use the Vertex AI API or the gcloud command-line tool to deploy the model to a Vertex AI endpoint, and provide the endpoint name, endpoint description, endpoint labels, and endpoint resources. A Vertex AI Model Monitoring job is a resource that can monitor the performance and quality of your deployed models on Vertex AI. A Vertex AI Model Monitoring job can help you detect and diagnose issues with your models, such as data drift, prediction drift, training/serving skew, or model staleness. Feature drift is a type of model monitoring metric that measures the difference between the distributions of the features used to train the model and the features used to serve the model over time. Feature drift can indicate that the online data is changing over time, and the model performance is degrading. By creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective, and providing an instance schema, you can monitor the feature distribution over time with minimal effort. You can use the Vertex AI API or the gcloud command-line tool to create a Vertex AI Model Monitoring job, and provide the monitoring objective, the monitoring frequency, the alerting threshold, and the notification channel. You can also provide an instance schema, which is a JSON file that describes the features and their types in the prediction input data. An instance schema can help Vertex AI Model Monitoring parse and analyze the string input format, and calculate the feature distributions and distance scores1.

The other options are not as good as option A, for the following reasons:

• Option B: Uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature skew detection as the monitoring objective, and providing an instance schema would not help you monitor the changes in the online data over time, and could cause errors or poor performance. Feature skew is a type of model monitoring metric that measures the difference between the distributions of the features used to train the model and the features used to serve the model at a given point in time. Feature skew can indicate that the model is not trained on the representative data, or that the data is changing over time. By creating a Vertex AI Model Monitoring job with feature skew detection as the monitoring objective, and providing an instance schema, you can monitor the feature distribution at a given point in time with minimal effort. However, uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature skew detection as the monitoring objective, and providing an instance schema would not help you monitor the changes in the online data over time, and could cause errors or poor performance. You would need to use the Vertex AI API or the gcloud command-line tool to upload the model to Vertex AI Model Registry, deploy the model to a Vertex AI endpoint, create a Vertex AI Model Monitoring job, and provide an instance schema. Moreover, this option would not monitor the feature drift, which is a more direct and relevant metric for measuring the changes in the online data over time, and the model performance and quality1.
• Option C: Refactoring the serving container to accept key-value pairs as input format, uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective would require more skills and steps than uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective, and providing an instance schema. A key-value pair input format is a type of input format that accepts a key-value pair as input for each prediction instance. A key-value pair input format can help you specify the feature names and values in a JSON object, and separate them by colons. By refactoring the serving container to accept key-value pairs as input format, uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective, you can serve and monitor your model with minimal code and configuration. You can write code to refactor the serving container to accept key-value pairs as input format, and use the Vertex AI API or the gcloud command-line tool to upload the model to Vertex AI Model Registry, deploy the model to a Vertex AI endpoint, and create a Vertex AI Model Monitoring job. However, refactoring the serving container to accept key-value pairs as input format, uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective would require more skills and steps than uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective, and providing an instance schema. You would need to write code, refactor the serving container, upload the model to Vertex AI Model Registry, deploy the model to a Vertex AI endpoint, and create a Vertex AI Model Monitoring job. Moreover, this option would not use the instance schema, which is a JSON file that can help Vertex AI Model Monitoring parse and analyze the string input format, and calculate the feature distributions and distance scores1.
• Option D: Refactoring the serving container to accept key-value pairs as input format, uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature skew detection as the monitoring objective would require more skills and steps than uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective, and providing an instance schema, and would not help you monitor the changes in the online data over time, and could cause errors or poor performance. Feature skew is a type of model monitoring metric that measures the difference between the distributions of the features used to train the model and the features used to serve the model at a given point in time. Feature skew can indicate that the model is not trained on the representative data, or that the data is changing over time. By creating a Vertex AI Model Monitoring job with feature skew detection as the monitoring objective, you can monitor the feature distribution at a given point in time with minimal effort. However, refactoring the serving container to accept key-value pairs as input format, uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature skew detection as the monitoring objective would require more skills and steps than uploading the model to Vertex AI Model Registry and deploying the model to a Vertex AI endpoint, creating a Vertex AI Model Monitoring job with feature drift detection as the monitoring objective, and providing an instance schema, and would not help you monitor the changes in the online data over time, and could cause errors or poor performance. You would need to write code, refactor the serving container, upload the model to Vertex AI Model Registry, deploy the model to a Vertex AI endpoint, and create a Vertex AI Model Monitoring job. Moreover, this option would not monitor the feature drift, which is a more direct and relevant metric for measuring the changes in the online data over time, and the model performance and quality1.

References:

• Using Model Monitoring | Vertex AI | Google Cloud

 AutoML Natural Language is a service that allows you to build and train custom natural language models without writing code. You can use AutoML Natural Language to perform sentiment analysis with custom categories, such as positive, negative, or neutral. You can also use pre-trained models or transfer learning to leverage existing knowledge and reduce the amount of data required to train a model from scratch. AutoML Natural Language provides a user-friendly interface and a powerful AutoML engine that optimizes your model for high predictive performance.

Cloud Natural Language API is a service that provides pre-trained models for common natural language tasks, such as sentiment analysis, entity analysis, and syntax analysis. However, it does not allow you to customize the categories or use your own data for training.

AI Hub pre-made Jupyter Notebooks are interactive documents that contain code, text, and visualizations for various machine learning scenarios. However, they require some coding skills and data preparation to use them effectively.

AI Platform Training built-in algorithms are pre-configured machine learning algorithms that you can use to train models on AI Platform. However, they do not support sentiment analysis as a natural language task.

References:

• AutoML Natural Language documentation
• Cloud Natural Language API documentation
• AI Hub documentation
• AI Platform Training documentation

According to the web search results, Cloud Build1 is a service that executes your builds on Google Cloud Platform infrastructure. Cloud Build can import source code from Cloud Source Repositories2, Cloud Storage, GitHub, Bitbucket, or any publicly hosted Git repository. Cloud Build allows you to create and manage build triggers, which are automated workflows that run whenever a code change is pushed to your source repository. You can use Cloud Build triggers to automatically retrain your ML models whenever there is any modification of the code. Therefore, option B is the best way to set up the CI pipeline for the given use case, as it allows you to configure a Cloud Build trigger with the event set as “Push to a branch”, which means the trigger will run whenever a new commit is pushed to a specific branch of your source repository. The other options are not relevant or optimal for this scenario. References:

• Cloud Build
• Cloud Source Repositories
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

The best option for dealing with the missing categorical variable in the test set is to apply one-hot encoding on the categorical variables in the test data. This option has the following advantages:

• It ensures the consistency and compatibility of the data format for the ML model, as the one-hot encoding transforms the categorical variables into binary vectors that can be easily processed by the model. By applying one-hot encoding on the categorical variables in the test data, you can match the number and order of the features in the test data with the training data, and avoid any errors or discrepancies in the model prediction.
• It preserves the information and relevance of the data for the ML model, as the one-hot encoding creates a separate feature for each possible value of the categorical variable, and assigns a value of 1 to the feature corresponding to the actual value of the variable, and 0 to the rest. By applying one-hot encoding on the categorical variables in the test data, you can retain the original meaning and importance of the categorical variable, and avoid any loss or distortion of the data.

The other options are less optimal for the following reasons:

• Option A: Randomly redistributing the data, with 70% for the training set and 30% for the test set, introduces additional complexity and risk. This option requires reshuffling and splitting the data again, which can be tedious and time-consuming. Moreover, this option may not guarantee that the missing categorical variable will be present in the test set, as it depends on the randomness of the data distribution. Furthermore, this option may affect the quality and validity of the ML model, as it may change the data characteristics and patterns that the model has learned from the original training set.
• Option B: Using sparse representation in the test set introduces additional overhead and inefficiency. This option requires converting the categorical variables in the test set into sparse vectors, which are vectors that have mostly zero values and only store the indices and values of the non-zero elements. However, using sparse representation in the test set may not be compatible with the ML model, as the model expects the input data to have the same format and dimensionality as the training data, which uses one-hot encoding. Moreover, using sparse representation in the test set may not be efficient or scalable, as it requires additional computation and memory to store and process the sparse vectors.
• Option D: Collecting more data representing all categories introduces additional cost and delay. This option requires obtaining and labeling more data that contains the missing categorical variable, which can be expensive and time-consuming. Moreover, this option may not be feasible or necessary, as the missing categorical variable may not be available or relevant for the test data, depending on the data source or the business problem.

In this scenario, the goal is to create a custom fraud detection model using AutoML Tables. Fraud detection is a type of binary classification problem, where the model needs to predict whether a transaction is fraudulent or not. The optimization objective is a metric that defines how the model is trained and evaluated. AutoML Tables allows you to choose from different optimization objectives for binary classification problems, such as Log loss, Precision at a Recall value, AUC PR, and AUC ROC.

To choose the best optimization objective for fraud detection, we need to consider the characteristics of the problem and the data. Fraud detection is a problem where the positive class (fraudulent transactions) is very rare compared to the negative class (legitimate transactions). This means that the data is highly imbalanced, and the model needs to be sensitive to the minority class. Moreover, fraud detection is a problem where the cost of false negatives (missing a fraudulent transaction) is much higher than the cost of false positives (flagging a legitimate transaction as fraudulent). This means that the model needs to have high recall (the ability to detect all fraudulent transactions) while maintaining high precision (the ability to avoid false alarms).

Given these considerations, the best optimization objective for fraud detection is the one that maximizes the area under the precision-recall curve (AUC PR) value. The AUC PR value is a metric that measures the trade-off between precision and recall for different probability thresholds. A higher AUC PR value means that the model can achieve high precision and high recall at the same time. The AUC PR value is also more suitable for imbalanced data than the AUC ROC value, which measures the trade-off between the true positive rate and the false positive rate. The AUC ROC value can be misleading for imbalanced data, as it can give a high score even if the model has low recall or low precision.

Therefore, option C is the correct answer. Option A is not suitable, as Log loss is a metric that measures the difference between the predicted probabilities and the actual labels, and does not account for the trade-off between precision and recall. Option B is not suitable, as Precision at a Recall value is a metric that measures the precision at a fixed recall level, and does not account for the trade-off between precision and recall at different thresholds. Option D is not suitable, as AUC ROC is a metric that can be misleading for imbalanced data, as explained above.

References:

• AutoML Tables documentation
• Optimization objectives for binary classification
• Precision-Recall Curves: How to Easily Evaluate Machine Learning Models in No Time
• ROC Curves and Area Under the Curve Explained (video)

• Option A is not the best answer because it requires using Apache Spark and Dataproc, which may incur additional cost and complexity for running and managing the cluster. It also requires saving the preprocessed data as CSV files in a Cloud Storage bucket, which may increase the storage cost and the data transfer latency.
• Option B is not the best answer because it requires loading the data into a pandas DataFrame, which may not be scalable or efficient for large datasets. It also requires training the model directly on the DataFrame, which may not leverage the distributed computing capabilities of BigQuery.
• Option C is the best answer because it allows performing preprocessing in BigQuery by using SQL, which is a cost-effective and efficient way to manipulate large datasets. It also allows using the BigQueryClient in TensorFlow to read the data directly from BigQuery, which is a convenient and fast way to access the data for training the model1.
• Option D is not the best answer because it requires using Apache Beam and Dataflow, which may incur additional cost and complexity for running and managing the pipeline. It also requires saving the preprocessed data as CSV files in a Cloud Storage bucket, which may increase the storage cost and the data transfer latency.

References:

• 1: Read data from BigQuery | TensorFlow I/O

• A fairness metric is a way to measure how well a machine learning model treats different groups of customers, such as by sex or age. A common fairness metric is accuracy, which is the proportion of correct predictions among all predictions. Accuracy across the sensitive features means calculating the accuracy for each group separately, and then comparing them. For example, if the model has 90% accuracy for male customers and 80% accuracy for female customers, there is a 10% accuracy gap that indicates potential bias against female customers.
• To investigate and mitigate potential bias, it is important to define a fairness metric and evaluate it on a test set. A test set is a subset of the data that is not used for training the model, but only for evaluating its performance. By joining the test set predictions with the sensitive features, you can calculate the fairness metric and see if it meets your requirements. For example, you may require that the accuracy gap between any two groups is less than 5%. If the fairness metric does not meet your requirements, you may need to adjust the model or the data to reduce bias.
• Option A is not the best answer because excluding the sensitive features and any meaningfully correlated features may not eliminate bias. For example, if salary is correlated with sex, and salary is also a predictive feature for the target variable, excluding both features may reduce the model accuracy and still leave some residual bias. Moreover, excluding features based on correlation may not capture the complex interactions and dependencies among the features that may affect bias.
• Option B is not the best answer because using the global attribution values for each feature of the model may not reflect the individual-level impact of the features on the predictions. Global attribution values are calculated by averaging the attribution values across all the data points, and they indicate how important each feature is for the overall model performance. However, they do not show how each feature affects each customer’s prediction, which may vary depending on the values of the other features. For example, sex may have a low global attribution value, but it may have a high impact on some customers’ predictions, especially if it interacts with other features such as salary or age.
• Option C is not the best answer because discarding the model and training the model again without a feature based on a single customer’s attribution value may not be a robust or scalable way to mitigate bias. Attribution values are calculated by measuring how much each feature contributes to the prediction for a given data point, and they indicate how sensitive the prediction is to the feature value. However, they do not show how the feature affects the overall fairness metric or the model accuracy. For example, sex may have a high attribution value for a customer, but it may not affect the accuracy gap between the groups. Moreover, discarding and retraining the model based on a single customer’s attribution value may not be feasible if there are many customers with high attribution values for different features.

 The problem of the text classifier is that it has a high false positive rate for comments that reference certain underrepresented religious groups. This means that the classifier is not able to distinguish between toxic and non-toxic language when those groups are mentioned. One possible reason for this is that the training data does not have enough examples of non-toxic comments that reference those groups, leading to a biased model. Therefore, a possible solution is to add synthetic training data where those phrases are used in non-toxic ways, which can help the model learn to generalize better and reduce the false positive rate. Synthetic data is artificially generated data that mimics the characteristics of real data, and can be used to augment the existing data when the real data is scarce or imbalanced. References:

• Preparing for Google Cloud Certification: Machine Learning Engineer, Course 5: Responsible AI, Week 3: Fairness
• Google Cloud Professional Machine Learning Engineer Exam Guide, Section 4: Ensuring solution quality, 4.4 Evaluating fairness and bias in ML models
• Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 9: Responsible AI, Section 9.3: Fairness and Bias

AI Platform supports hyperparameter tuning for PyTorch models using custom containers. This allows you to use any Python dependencies and libraries that are not included in the pre-built AI Platform Training runtime versions. You can also use a pre-trained model such as ResNet as a base for your custom model. To run a hyperparameter tuning job on AI Platform using custom containers, you need to do the following steps:

• Create a Dockerfile that defines the container image for your training application. The Dockerfile should install PyTorch and any other dependencies, copy your training code and configuration files, and set the entrypoint for the container.
• Build the container image and push it to Container Registry or another accessible registry.
• Create a YAML file that defines the configuration for your hyperparameter tuning job. The YAML file should specify the container image URI, the training input and output paths, the hyperparameters to tune, the metric to optimize, and the tuning algorithm and budget.
• Submit the hyperparameter tuning job to AI Platform using the gcloud command-line tool or the AI Platform Training API.

References:

• Hyperparameter tuning overview
• Using custom containers
• PyTorch on AI Platform Training

 Vertex AI Experiments is a service that allows you to track, compare, and optimize your ML experiments on Google Cloud. You can use Vertex AI Experiments to log metrics and parameters from your TensorFlow models, and then visualize them in Vertex AI TensorBoard. Vertex AI TensorBoard is a managed service that provides a web interface for viewing and debugging your ML experiments. You can use Vertex AI TensorBoard to compare different runs, inspect model graphs, analyze scalars, histograms, images, and more. By using Vertex AI Experiments and Vertex AI TensorBoard, you can simplify your ML experiment tracking and visualization workflow, and avoid the overhead of setting up and maintaining your own Cloud Functions, Cloud Storage buckets, or VMs. References:

• [Vertex AI Experiments documentation]
• [Vertex AI TensorBoard documentation]
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

 According to the official exam guide1, one of the skills assessed in the exam is to “automate and orchestrate ML pipelines using Cloud Composer”. Cloud Composer2 is a fully managed workflow orchestration service that uses Apache Airflow to create, schedule, monitor, and manage workflows. Cloud Composer allows you to build custom training pipelines for deep learning-based models and integrate them with other Google Cloud services. You can also use Cloud Composer to implement model interpretability techniques, such as feature attributions, explainable AI, or model debugging3. The other options are not relevant or optimal for this scenario. References:

• Professional ML Engineer Exam Guide
• Cloud Composer
• Model interpretability with Cloud Composer
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

 The best option for configuring the workflow is to add the transformations as a preprocessing layer in the TensorFlow models. This option allows you to leverage the power and simplicity of TensorFlow to preprocess and transform the data with simple Python code. TensorFlow is a framework for building and training machine learning models. TensorFlow provides various tools and libraries for data analysis and machine learning. A preprocessing layer is a type of layer in TensorFlow that can perform data preprocessing and feature engineering operations on the input data. A preprocessing layer can help you customize the data transformation and preprocessing logic, and handle complex or non-standard data formats. A preprocessing layer can also help you minimize the preprocessing time, cost, and development effort, as you only need to write a few lines of code to implement the preprocessing layer, and you do not need to create any intermediate data sources or pipelines. By adding the transformations as a preprocessing layer in the TensorFlow models, you can use Vertex AI’s custom training service to train multiple TensorFlow models that read the data from BigQuery and predict future sales1.

The other options are not as good as option C, for the following reasons:

• Option A: Writing the transformations into Spark that uses the spark-bigquery-connector and using Dataproc to preprocess the data would require more skills and steps than using a preprocessing layer in TensorFlow. Spark is a framework for distributed data processing and machine learning. Spark can read and write data from BigQuery by using the spark-bigquery-connector, which is a library that allows Spark to communicate with BigQuery. Dataproc is a service that can create and manage Spark clusters on Google Cloud. Dataproc can help you run Spark jobs on Google Cloud, and scale the clusters according to the workload. However, writing the transformations into Spark that uses the spark-bigquery-connector and using Dataproc to preprocess the data would require more skills and steps than using a preprocessing layer in TensorFlow. You would need to write code, create and configure the Spark cluster, install and import the spark-bigquery-connector, load and preprocess the data, and write the data back to BigQuery. Moreover, this option would create an intermediate data source in BigQuery, which can increase the storage and computation costs2.
• Option B: Writing SQL queries to transform the data in-place in BigQuery would not allow you to use Vertex AI’s custom training service to train multiple TensorFlow models that read the data from BigQuery and predict future sales. BigQuery is a service that can perform data analysis and machine learning by using SQL queries. BigQuery can perform data transformation and preprocessing by using SQL functions and clauses, such as MIN, MAX, CASE, and TRANSFORM. BigQuery can also perform machine learning by using BigQuery ML, which is a feature that can create and train machine learning models by using SQL queries. However, writing SQL queries to transform the data in-place in BigQuery would not allow you to use Vertex AI’s custom training service to train multiple TensorFlow models that read the data from BigQuery and predict future sales. Vertex AI’s custom training service is a service that can run your custom machine learning code on Vertex AI. Vertex AI’s custom training service can support various machine learning frameworks, such as TensorFlow, PyTorch, and scikit-learn. Vertex AI’s custom training service cannot support SQL queries, as SQL is not a machine learning framework. Therefore, if you want to use Vertex AI’s custom training service, you cannot use SQL queries to transform the data in-place in BigQuery3.
• Option D: Creating a Dataflow pipeline that uses the BigQueryIO connector to ingest the data, process it, and write it back to BigQuery would require more skills and steps than using a preprocessing layer in TensorFlow. Dataflow is a service that can create and run data processing and machine learning pipelines on Google Cloud. Dataflow can read and write data from BigQuery by using the BigQueryIO connector, which is a library that allows Dataflow to communicate with BigQuery. Dataflow can perform data transformation and preprocessing by using Apache Beam, which is a framework for distributed data processing and machine learning. However, creating a Dataflow pipeline that uses the BigQueryIO connector to ingest the data, process it, and write it back to BigQuery would require more skills and steps than using a preprocessing layer in TensorFlow. You would need to write code, create and configure the Dataflow pipeline, install and import the BigQueryIO connector, load and preprocess the data, and write the data back to BigQuery. Moreover, this option would create an intermediate data source in BigQuery, which can increase the storage and computation costs4.

References:

• Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 2: Serving ML Predictions
• Google Cloud Professional Machine Learning Engineer Exam Guide, Section 2: Developing ML models, 2.1 Developing ML models by using TensorFlow
• Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 4: Developing ML Models, Section 4.1: Developing ML Models by Using TensorFlow
• TensorFlow Preprocessing Layers
• Spark and BigQuery
• Dataproc
• BigQuery ML
• Dataflow and BigQuery
• Apache Beam

 Overfitting occurs when a model tries to fit the training data so closely that it does not generalize well to new data. Overfitting can be caused by having a model that is too complex for the data, such as having too many parameters or layers. Overfitting can lead to poor performance on the validation data, which reflects how the model will perform on unseen data1

To prevent overfitting, one strategy is to use regularization techniques that penalize the complexity of the model and encourage it to learn simpler patterns. Two common regularization techniques for deep neural networks are L2 regularization and dropout. L2 regularization adds a term to the loss function that is proportional to the squared magnitude of the model’s weights. This term penalizes large weights and encourages the model to use smaller weights. Dropout randomly drops out some units in the network during training, which prevents co-adaptation of features and reduces the effective number of parameters. Both L2 regularization and dropout have hyperparameters that control the strength of the regularization effect23

Another strategy to prevent overfitting is to use hyperparameter tuning, which is the process of finding the optimal values for the parameters of the model that affect its performance. Hyperparameter tuning can help find the best combination of hyperparameters that minimize the validation loss and improve the generalization ability of the model. AI Platform provides a service for hyperparameter tuning that can run multiple trials in parallel and use different search algorithms to find the best solution.

Therefore, the best strategy to use when retraining the model is to run a hyperparameter tuning job on AI Platform to optimize for the L2 regularization and dropout parameters. This will allow the model to find the optimal balance between fitting the training data and generalizing to new data. The other options are not as effective, as they either use fixed values for the regularization parameters, which may not be optimal, or they do not address the issue of overfitting at all.

References: 1: Generalization: Peril of Overfitting 2: Regularization for Deep Learning 3: Dropout: A Simple Way to Prevent Neural Networks from Overfitting : [Hyperparameter tuning overview]

The best option to build a comprehensive system that recommends images to users that are similar in appearance to their own uploaded images is to download a pretrained convolutional neural network (CNN), and use the model to generate embeddings of the input images. Embeddings are low-dimensional representations of high-dimensional data that capture the essential features and semantics of the data. By using a pretrained CNN, you can leverage the knowledge learned from large-scale image datasets, such as ImageNet, and apply it to your own domain. A pretrained CNN can be used as a feature extractor, where the output of the last hidden layer (or any intermediate layer) is taken as the embedding vector for the input image. You can then measure the similarity between embeddings using a distance metric, such as cosine similarity or Euclidean distance, and recommend images that have the highest similarity scores to the user’s uploaded image. Option A is incorrect because downloading a pretrained CNN and fine-tuning the model to predict hashtags based on the input images may not capture the visual similarity of the images, as hashtags may not reflect the appearance of the images accurately. For example, two images of different breeds of dogs may have the same hashtag #dog, but they may not look similar to each other. Moreover, fine-tuning the model may require additional data and computational resources, and it may not generalize well to new images that have different or missing hashtags. Option B is incorrect because retrieving image labels and dominant colors from the input images using the Vision API may not capture the visual similarity of the images, as labels and colors may not reflect the fine-grained details of the images. For example, two images of the same breed of dog may have different labels and colors depending on the background, lighting, and angle of the image. Moreover, using the Vision API may incur additional costs and latency, and it may not be able to handle custom or domain-specific labels. Option C is incorrect because using the provided hashtags to create a collaborative filtering algorithm may not capture the visual similarity of the images, as collaborative filtering relies on the ratings or preferences of users, not the features of the images. For example, two images of different animals may have similar ratings or preferences from users, but they may not look similar to each other. Moreover, collaborative filtering may suffer from the cold start problem, where new images or users that have no ratings or preferences cannot be recommended. References:

• Image similarity search with TensorFlow
• Image embeddings documentation
• Pretrained models documentation
• Similarity metrics documentation

 AutoML Natural Language is a service that allows users to create custom natural language models using their own data and labels. It supports various natural language tasks, such as text classification, entity extraction, and sentiment analysis. AutoML Natural Language can be used to build a model to classify incoming calls by product, as it can extract custom entities from the transcribed calls and assign them to predefined categories. AutoML Natural Language also minimizes data preprocessing and development time, as it handles the data preparation, model training, and evaluation automatically. The other options are not as suitable for this scenario. AI Platform Training built-in algorithms are a set of pre-defined algorithms that can be used to train ML models on AI Platform, but they do not support natural language processing tasks. Cloud Natural Language API is a pre-trained service that provides natural language understanding capabilities, such as sentiment analysis, entity analysis, syntax analysis, and content classification. However, it does not support custom entities or categories, and may not recognize the product names from the calls. Building a custom model to identify the product keywords and then running them through a classification algorithm would require more data preprocessing and development time, as well as more coding and testing. References:

• AutoML Natural Language documentation
• AI Platform Training built-in algorithms documentation
• Cloud Natural Language API documentation

• Option A is incorrect because implementing continuous retraining of the model daily using Vertex AI Pipelines is not the most efficient way to prevent prediction drift. Vertex AI Pipelines is a service that allows you to create and run scalable and portable ML pipelines on Google Cloud1. You can use Vertex AI Pipelines to retrain your model daily using the latest data from the BigQuery table. However, this option may be unnecessary or wasteful, as the data distribution may not change significantly every day, and retraining the model may consume a lot of resources and time. Moreover, this option does not monitor the model performance or detect the prediction drift, which are essential steps for ensuring the quality and reliability of the model.
• Option B is correct because adding a model monitoring job where 10% of incoming predictions are sampled 24 hours is the best way to prevent prediction drift. Model monitoring is a service that allows you to track the performance and health of your deployed models over time2. You can use model monitoring to sample a fraction of the incoming predictions and compare them with the ground truth labels, which can be obtained from the BigQuery table or other sources. You can also use model monitoring to compute various metrics, such as accuracy, precision, recall, or F1-score, and set thresholds or alerts for them. By using model monitoring, you can detect and diagnose the prediction drift, and decide when to retrain or update your model. Sampling 10% of the incoming predictions every 24 hours is a reasonable choice, as it balances the trade-off between the accuracy and the cost of the monitoring job.
• Option C is incorrect because adding a model monitoring job where 90% of incoming predictions are sampled 24 hours is not a optimal way to prevent prediction drift. This option has the same advantages as option B, as it uses model monitoring to track the performance and health of the deployed model. However, this option is not cost-effective, as it samples a very large fraction of the incoming predictions, which may incur a lot of storage and processing costs. Moreover, this option may not improve the accuracy of the monitoring job significantly, as sampling 10% of the incoming predictions may already provide a representative sample of the data distribution.
• Option D is incorrect because adding a model monitoring job where 10% of incoming predictions are sampled every hour is not a necessary way to prevent prediction drift. This option also has the same advantages as option B, as it uses model monitoring to track the performance and health of the deployed model. However, this option may be excessive, as it samples the incoming predictions too frequently, which may not reflect the actual changes in the data distribution. Moreover, this option may incur more storage and processing costs than option B, as it generates more samples and metrics.

References:

• Vertex AI Pipelines documentation
• Model monitoring documentation
• [Prediction drift]
• [TensorFlow Extended documentation]
• [BigQuery documentation]
• [Vertex AI documentation]

The best option for creating a scalable and maintainable production process that runs end-to-end and tracks the connections between steps, using prototype code to production, feature engineering code in PySpark that runs on Dataproc Serverless, and model training that is executed by using a Vertex AI custom training job, is to use the Kubeflow pipelines SDK to write code that specifies two components. The first is a Dataproc Serverless component that launches the feature engineering job. The second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job. This option allows you to leverage the power and simplicity of Kubeflow pipelines to orchestrate and automate your machine learning workflows on Vertex AI. Kubeflow pipelines is a platform that can build, deploy, and manage machine learning pipelines on Kubernetes. Kubeflow pipelines can help you create reusable and scalable pipelines, experiment with different pipeline versions and parameters, and monitor and debug your pipelines. Kubeflow pipelines SDK is a set of Python packages that can help you build and run Kubeflow pipelines. Kubeflow pipelines SDK can help you define pipeline components, specify pipeline parameters and inputs, and create pipeline steps and tasks. A component is a self-contained set of code that performs one step in a pipeline, such as data preprocessing, model training, or model evaluation. A component can be created from a Python function, a container image, or a prebuilt component. A custom component is a component that is not provided by Kubeflow pipelines, but is created by the user to perform a specific task. A custom component can be wrapped in a utility function that can help you create a Vertex AI custom training job from the component. A custom training job is a resource that can run your custom training code on Vertex AI. A custom training job can help you train various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, and deep neural networks. By using the Kubeflow pipelines SDK to write code that specifies two components, the first is a Dataproc Serverless component that launches the feature engineering job, and the second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job, you can create a scalable and maintainable production process that runs end-to-end and tracks the connections between steps. You can write code that defines the two components, their inputs and outputs, and their dependencies. You can then use the Kubeflow pipelines SDK to create a pipeline that runs the two components in sequence, and submit the pipeline to Vertex AI Pipelines for execution. By using Dataproc Serverless component, you can run your PySpark feature engineering code on Dataproc Serverless, which is a service that can run Spark batch workloads without provisioning and managing your own cluster. By using custom component wrapped in the create_custom_training_job_from_component utility, you can run your custom model training code on Vertex AI, which is a unified platform for building and deploying machine learning solutions on Google Cloud1.

The other options are not as good as option C, for the following reasons:

• Option A: Creating a Vertex AI Workbench notebook, using the notebook to submit the Dataproc Serverless feature engineering job, using the same notebook to submit the custom model training job, and running the notebook cells sequentially to tie the steps together end-to-end would require more skills and steps than using the Kubeflow pipelines SDK to write code that specifies two components, the first is a Dataproc Serverless component that launches the feature engineering job, and the second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job. Vertex AI Workbench is a service that can provide managed notebooks for machine learning development and experimentation. Vertex AI Workbench can help you create and run JupyterLab notebooks, and access various tools and frameworks, such as TensorFlow, PyTorch, and JAX. By creating a Vertex AI Workbench notebook, using the notebook to submit the Dataproc Serverless feature engineering job, using the same notebook to submit the custom model training job, and running the notebook cells sequentially to tie the steps together end-to-end, you can create a production process that runs end-to-end and tracks the connections between steps. You can write code that submits the Dataproc Serverless feature engineering job and the custom model training job to Vertex AI, and run the code in the notebook cells. However, creating a Vertex AI Workbench notebook, using the notebook to submit the Dataproc Serverless feature engineering job, using the same notebook to submit the custom model training job, and running the notebook cells sequentially to tie the steps together end-to-end would require more skills and steps than using the Kubeflow pipelines SDK to write code that specifies two components, the first is a Dataproc Serverless component that launches the feature engineering job, and the second is a custom component wrapped in the create_custom_training_job_from_component utility that launches the custom model training job. You would need to write code, create and configure the Vertex AI Workbench notebook, submit the Dataproc Serverless feature engineering job and the custom model training job, and run the notebook cells. Moreover, this option would not use the Kubeflow pipelines SDK, which can simplify the pipeline creation and execution process, and provide various features, such as pipeline parameters, pipeline metrics, and pipeline visualization2.
• Option B: Creating a Vertex AI Workbench notebook, initiating an Apache Spark context in the notebook, and running the PySpark feature engineering code, using the same notebook to run the custom model training job in TensorFlow, and running the notebook cells sequentially to tie the steps together end-to-end would not allow you to use Dataproc Serverless to run the feature engineering job, and could increase the complexity and cost of the production process. Apache Spark is a framework that can perform large-scale data processing and machine learning. Apache Spark can help you run various tasks, such as data ingestion, data transformation, data analysis, and data visualization. PySpark is a Python API for Apache Spark. PySpark can help you write and run Spark code in Python. An Apache Spark context is a resource that can initialize and configure the Spark environment. An Apache Spark context can help you create and manage Spark objects, such as SparkSession, SparkConf, and SparkContext. By creating a Vertex AI Workbench notebook, initiating an Apache Spark context in the notebook, and running the PySpark feature engineering code, using the same notebook to run the custom model training job in TensorFlow, and running the notebook cells sequentially to tie the steps together end-to-end, you can create a production process that runs end-to-end and tracks the connections between steps. You can write code that initiates an Apache Spark context and runs the PySpark feature engineering code, and runs the custom model training job in TensorFlow, and run the code in the notebook cells. However, creating a Vertex AI Workbench notebook, initiating an Apache Spark context in the notebook, and running the PySpark feature engineering code, using the same notebook to run the custom model training job in TensorFlow, and running the notebook cells sequentially to tie the steps together end-to-end would not allow you to use Dataproc Serverless to run the feature engineering job, and could increase the complexity and cost of the production process. You would need to write code, create and configure the Vertex AI Workbench notebook, initiate and configure the Apache Spark context, run the PySpark feature engineering code, and run the custom model training job in TensorFlow. Moreover, this option would not use Dataproc Serverless, which is a service that can run Spark batch workloads without provisioning and managing your own cluster, and provide various benefits, such as autoscaling, dynamic resource allocation, and serverless billing2.
• Option D: Creating a Vertex AI Pipelines job to link and run both components, using the Kubeflow pipelines SDK to write code that specifies two components, the first component initiates an Apache Spark context that runs the PySpark feature engineering code, and the second component runs the TensorFlow custom model training code, would not allow you to use Dataproc Serverless to run the feature engineering job, and could increase the complexity and cost of the production process. Vertex AI Pipelines is a service that can run Kubeflow pipelines on Vertex AI. Vertex AI Pipelines can help you create and manage machine learning pipelines, and integrate with various Vertex AI services, such as Vertex AI Workbench, Vertex AI Training, and Vertex AI Prediction. A Vertex AI Pipelines job is a resource that can execute a pipeline on Vertex AI Pipelines. A Vertex AI Pipelines job can help you run your pipeline steps and tasks, and monitor and debug your pipeline execution. By creating a Vertex AI Pipelines job to link and run both components, using the Kubeflow pipelines SDK to write code that specifies two components, the first component initiates an Apache Spark context that runs the PySpark feature engineering code, and the second component runs the TensorFlow custom model training code, you can create a scalable and maintainable production process that runs end-to-end and tracks the connections between steps. You can write code that defines the two components, their inputs and outputs, and their dependencies. You can then use the Kubeflow pipelines SDK to create a pipeline that runs the two components in sequence, and submit the pipeline to Vertex AI Pipelines for execution. However, creating a Vertex AI Pipelines job to link and run both components, using the Kubeflow pipelines SDK to write code that specifies two components, the first component initiates an Apache Spark context that runs the PySpark feature engineering code,

An input pipeline is a way to prepare and feed data to a machine learning model for training or inference. An input pipeline typically consists of several steps, such as reading, parsing, transforming, batching, and prefetching the data. An input pipeline can improve the performance and efficiency of the model, as it can handle large and complex datasets, optimize the data processing, and reduce the latency and memory usage1.

For the use case of developing an input pipeline for an ML training model that processes images from disparate sources at a low latency, the best option is to convert the images into TFRecords, store the images in Cloud Storage, and then use the tf.data API to read the images for training. This option involves using the following components and techniques:

• TFRecords: TFRecords is a binary file format that can store a sequence of data records, such as images, text, or audio. TFRecords can help to compress, serialize, and store the data efficiently, and reduce the data loading and parsing time. TFRecords can also support data sharding and interleaving, which can improve the data throughput and parallelism2.
• Cloud Storage: Cloud Storage is a service that allows you to store and access data on Google Cloud. Cloud Storage can help to store and manage large and distributed datasets, such as images from different sources, and provide high availability, durability, and scalability. Cloud Storage can also integrate with other Google Cloud services, such as Compute Engine, AI Platform, and Dataflow3.
• tf.data API: tf.data API is a set of tools and methods that allow you to create and manipulate data pipelines in TensorFlow. tf.data API can help to read, transform, batch, and prefetch the data efficiently, and optimize the data processing for performance and memory. tf.data API can also support various data sources and formats, such as TFRecords, CSV, JSON, and images.

By using these components and techniques, the input pipeline can process large datasets of images from disparate sources that do not fit in memory, and provide low latency and high performance for the ML training model. Therefore, converting the images into TFRecords, storing the images in Cloud Storage, and using the tf.data API to read the images for training is the best option for this use case.

References:

• Build TensorFlow input pipelines | TensorFlow Core
• TFRecord and tf.Example | TensorFlow Core
• Cloud Storage documentation | Google Cloud
• [tf.data: Build TensorFlow input pipelines | TensorFlow Core]

This option is the best way to architect the workflow, as it allows you to use event-driven and serverless components to automate the ML training process. Cloud Storage triggers are a feature that allows you to send notifications to a Pub/Sub topic when an object is created, deleted, or updated in a storage bucket. Pub/Sub is a service that allows you to publish and subscribe to messages on various topics. Pub/Sub-triggered Cloud Functions are a type of Cloud Functions that are invoked when a message is published to a specific Pub/Sub topic. Cloud Functions are a serverless platform that allows you to run code in response to events. By using these components, you can create a workflow that starts the training job on a GKE cluster as soon as a new file is available in the Cloud Storage bucket, without having to manage any servers or poll for changes. The other options are not as efficient or scalable as this option. Dataflow is a service that allows you to create and run data processing pipelines, but it is not designed to trigger ML training jobs on GKE. App Engine is a service that allows you to build and deploy web applications, but it is not suitable for polling Cloud Storage for new files, as it may incur unnecessary costs and latency. Cloud Scheduler is a service that allows you to schedule jobs at regular intervals, but it is not ideal for triggering ML training jobs based on data availability, as it may miss some files or run unnecessary jobs. References:

• Cloud Storage triggers documentation
• Pub/Sub documentation
• Pub/Sub-triggered Cloud Functions documentation
• Cloud Functions documentation
• Kubeflow Pipelines documentation

 The best option for determining how often to retrain your model to maintain a high level of performance while minimizing cost is to run training-serving skew detection batch jobs every few days. Training-serving skew refers to the discrepancy between the distributions of the features in the training dataset and the serving data. This can cause the model to perform poorly on the new data, as it is not representative of the data that the model was trained on. By running training-serving skew detection batch jobs, you can monitor the changes in the feature distributions over time, and identify when the skew becomes significant enough to affect the model performance. If skew is detected, you can send the most recent serving data to the labeling service, and use the labeled data to retrain your model. This option has the following benefits:

• It allows you to retrain your model only when necessary, based on the actual data changes, rather than on a fixed schedule or a heuristic. This can save you the cost of the labeling service and the retraining process, and also avoid overfitting or underfitting your model.
• It leverages the existing tools and frameworks for training-serving skew detection, such as TensorFlow Data Validation (TFDV) and Vertex Data Labeling. TFDV is a library that can compute and visualize descriptive statistics for your datasets, and compare the statistics across different datasets. Vertex Data Labeling is a service that can label your data with high quality and low latency, using either human labelers or automated labelers.
• It integrates well with the MLOps practices, such as continuous integration and continuous delivery (CI/CD), which can automate the workflow of running the skew detection jobs, sending the data to the labeling service, retraining the model, and deploying the new model version.

The other options are less optimal for the following reasons:

• Option A: Training an anomaly detection model on the training dataset, and running all incoming requests through this model, introduces additional complexity and overhead. This option requires building and maintaining a separate model for anomaly detection, which can be challenging and time-consuming. Moreover, this option requires running the anomaly detection model on every request, which can increase the latency and resource consumption of the prediction service. Additionally, this option may not capture the subtle changes in the feature distributions that can affect the model performance, as anomalies are usually defined as rare or extreme events.
• Option B: Identifying temporal patterns in your model’s performance over the previous year, and creating a schedule for sending serving data to the labeling service for the next year, introduces additional assumptions and risks. This option requires analyzing the historical data and model performance, and finding the patterns that can explain the variations in the model performance over time. However, this can be difficult and unreliable, as the patterns may not be consistent or predictable, and may depend on various factors that are not captured by the data. Moreover, this option requires creating a schedule based on the past patterns, which may not reflect the future changes in the data or the environment. This can lead to either sending too much or too little data to the labeling service, resulting in either wasted cost or degraded performance.
• Option C: Comparing the cost of the labeling service with the lost revenue due to model performance degradation over the past year, and adjusting the frequency of model retraining accordingly, introduces additional challenges and trade-offs. This option requires estimating the cost of the labeling service and the lost revenue due to model performance degradation, which can be difficult and inaccurate, as they may depend on various factors that are not easily quantifiable or measurable. Moreover, this option requires finding the optimal balance between the cost and the performance, which can be subjective and variable, as different stakeholders may have different preferences and expectations. Furthermore, this option may not account for the potential impact of the model performance degradation on other aspects of the business, such as customer satisfaction, retention, or loyalty.

AI Platform Notebooks is a service that provides managed Jupyter notebooks for data science and machine learning. You can use AI Platform Notebooks to create, run, and share your code and analysis in a collaborative and interactive environment1. BigQuery is a service that allows you to analyze large-scale and complex data using SQL queries. You can use BigQuery to stream, store, and query your data in a fast and cost-effective way2. Pandas is a popular Python library that provides data structures and tools for data analysis and manipulation. You can use pandas to create, manipulate, and visualize dataframes, which are tabular data structures with rows and columns3.

AI Platform Notebooks provides a cell magic, %%bigquery, that allows you to run SQL queries on BigQuery data and ingest the results as a pandas dataframe. A cell magic is a special command that applies to the whole cell in a Jupyter notebook. The %%bigquery cell magic can take various arguments, such as the name of the destination dataframe, the name of the destination table in BigQuery, the project ID, and the query parameters4. By using the %%bigquery cell magic, you can query the data in BigQuery with minimal code and manipulate the results with pandas in AI Platform Notebooks. This is the most convenient and efficient way to achieve your goal.

The other options are not as good as option A, because they involve more steps, more code, and more manual effort. Option B requires you to export your table as a CSV file from BigQuery to Google Drive, and then use the Google Drive API to ingest the file into your notebook instance. This option is cumbersome and time-consuming, as it involves moving the data across different services and formats. Option C requires you to download your table from BigQuery as a local CSV file, and then upload it to your AI Platform notebook instance. This option is also inefficient and impractical, as it involves downloading and uploading large files, which can take a long time and consume a lot of bandwidth. Option D requires you to use a bash cell in your AI Platform notebook to export the table as a CSV file to Cloud Storage, and then copy the data into the notebook. This option is also complex and unnecessary, as it involves using different commands and tools to move the data around. Therefore, option A is the best option for this use case.

References:

• AI Platform Notebooks documentation
• BigQuery documentation
• pandas documentation
• Using Jupyter magics to query BigQuery data

• Monitoring model performance is an essential part of production readiness, as it allows the team to detect and address any issues that may arise after deployment, such as data drift, model degradation, or errors.
• Other Options:

According to the web search results, TensorFlow Extended (TFX) is a platform for building end-to-end machine learning pipelines using TensorFlow1. TFX provides a set of components that can be orchestrated using either the TFX SDK or Kubeflow Pipelines. TFX components can handle different aspects of the pipeline, such as data ingestion, data validation, data transformation, model training, model evaluation, model serving, and more. TFX components can also leverage other Google Cloud services, such as Dataflow2 and Vertex AI3. Dataflow is a fully managed service for running Apache Beam pipelines on Google Cloud. Dataflow handles the provisioning and management of the compute resources, as well as the optimization and execution of the pipelines. Vertex AI is a unified platform for machine learning development and deployment. Vertex AI offers various services and tools for building, managing, and serving machine learning models. Therefore, option D is the best way to create a low maintenance, automated workflow for the given use case, as it allows you to use the TFX SDK to define and execute your pipeline components, and use Dataflow and Vertex AI services to scale and optimize your pipeline. The other options are not relevant or optimal for this scenario. References:

• TensorFlow Extended
• Dataflow
• Vertex AI
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

The best option for handling missing data in this case is to predict the missing values using linear regression. Linear regression is a supervised learning technique that can be used to estimate the relationship between a continuous target variable and one or more predictor variables. In this case, the target variable is the distance from the closest school, and the predictor variables are the other features in the dataset, such as house size, location, number of rooms, etc. By fitting a linear regression model on the data that has no missing values, we can then use the model to predict the missing values for the distance from the closest school feature. This way, we can preserve all the instances in the dataset and avoid introducing bias or reducing variance. The other options are not suitable for handling missing data in this case, because:

• Deleting the rows that have missing values would reduce the size of the dataset and potentially lose important information. Since every instance is important, we want to keep as much data as possible.
• Applying feature crossing with another column that does not have missing values would create a new feature that combines the values of two existing features. This might increase the complexity of the model and introduce noise or multicollinearity. It would not solve the problem of missing values, as the new feature would still have missing values whenever the distance from the closest school feature is missing.
• Replacing the missing values with zeros would distort the distribution of the feature and introduce bias. It would also imply that the houses with missing values are located at the same distance from the closest school, which is unlikely to be true. A zero value might also be outside the range of the feature, as the distance from the closest school is unlikely to be exactly zero for any house. References:
• Linear Regression
• Imputation of missing values
• Google Cloud launches machine learning engineer certification
• Google Professional Machine Learning Engineer Certification
• Professional ML Engineer Exam Guide
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

According to the official exam guide1, one of the skills assessed in the exam is to “explain the predictions of a trained model”. Vertex AI provides feature attributions using Shapley Values, a cooperative game theory algorithm that assigns credit to each feature in a model for a particular outcome2. Feature attributions can help you understand how the model calculates the predictions and debug or optimize the model accordingly. You can use AutoML for Tabular Data to generate and query local feature attributions3. The other options are not relevant or optimal for this scenario. References:

• Professional ML Engineer Exam Guide
• Feature attributions for classification and regression
• AutoML for Tabular Data
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

AutoML Vision Edge is a service that allows you to create custom image classification and object detection models that can run on edge devices, such as mobile phones, tablets, or IoT devices1. AutoML Vision Edge offers four types of models that vary in size, accuracy, and latency: mobile-versatile-1, mobile-low-latency-1, mobile-high-accuracy-1, and mobile-core-ml-low-latency-12. Each model has its own trade-offs and use cases, depending on the device specifications and the application requirements.

For the use case of building an ML model to reduce the amount of time spent by quality control inspectors checking for product defects, the best model to use is the AutoML Vision Edge mobile-low-latency-1 model. This model is optimized for fast inference on mobile devices, with a latency of less than 50 milliseconds on a Pixel 1 phone2. Faster defect detection is a priority for the toy manufacturer, and the factory does not have reliable Wi-Fi, so a low-latency model that can run on the device without internet connection is ideal. The mobile-low-latency-1 model also has a small size of less than 4 MB, which makes it easy to deploy and update2. The mobile-low-latency-1 model has a slightly lower accuracy than the mobile-high-accuracy-1 model, but it is still suitable for most image classification tasks2. Therefore, the AutoML Vision Edge mobile-low-latency-1 model is the best option for this use case.

References:

• AutoML Vision Edge documentation
• AutoML Vision Edge model types

Z-score normalization is a technique that transforms the values of a numeric variable into standardized units, such that the mean is zero and the standard deviation is one. Z-score normalization can help to compare variables with different scales and ranges, and to reduce the effect of outliers and skewness. The formula for z-score normalization is:

z = (x - mu) / sigma

where x is the original value, mu is the mean of the variable, and sigma is the standard deviation of the variable.

Dataflow is a service that allows you to create and run data processing pipelines on Google Cloud. You can use Dataflow to preprocess raw data prior to model training and prediction, such as applying z-score normalization on data stored in BigQuery. However, using Dataflow for this task may not be the most efficient option, as it involves reading and writing data from and to BigQuery, which can be time-consuming and costly. Moreover, using Dataflow requires manual intervention to update the pipeline whenever new training data is added.

A more efficient way to perform z-score normalization on data stored in BigQuery is to translate the normalization algorithm into SQL and use it with BigQuery. BigQuery is a service that allows you to analyze large-scale and complex data using SQL queries. You can use BigQuery to perform z-score normalization on your data using SQL functions such as AVG(), STDDEV_POP(), and OVER(). For example, the following SQL query can normalize the values of a column called temperature in a table called weather:

SELECT (temperature - AVG(temperature) OVER ()) / STDDEV_POP(temperature) OVER () AS normalized_temperature FROM weather;

By using SQL to perform z-score normalization on BigQuery, you can make the process more efficient by minimizing computation time and manual intervention. You can also leverage the scalability and performance of BigQuery to handle large and complex datasets. Therefore, translating the normalization algorithm into SQL for use with BigQuery is the best option for this use case.

 The best option for splitting the data between the training, validation, and test sets, using a managed tabular dataset in Vertex AI that contains sales data from three different stores, is to use Vertex AI default data split. This option allows you to leverage the power and simplicity of Vertex AI to automatically and randomly split your data into the three sets by percentage. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can support various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, and deep neural networks. Vertex AI can also provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance. A default data split is a data split method that is provided by Vertex AI, and does not require any user input or configuration. A default data split can help you split your data into the training, validation, and test sets by using a random sampling method, and assign a fixed percentage of the data to each set. A default data split can help you simplify the data split process, and works well in most cases. A training set is a subset of the data that is used to train the model, and adjust the model parameters. A training set can help you learn the relationship between the input features and the target variable, and optimize the model performance. A validation set is a subset of the data that is used to validate the model, and tune the model hyperparameters. A validation set can help you evaluate the model performance on unseen data, and avoid overfitting or underfitting. A test set is a subset of the data that is used to test the model, and provide the final evaluation metrics. A test set can help you assess the model performance on new data, and measure the generalization ability of the model. By using Vertex AI default data split, you can split your data into the training, validation, and test sets by using a random sampling method, and assign the following percentages of the data to each set1:

The other options are not as good as option B, for the following reasons:

• Option A: Using Vertex AI manual split, using the store name feature to assign one store for each set would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. A manual split is a data split method that allows you to control how your data is split into sets, by using the ml_use label or the data filter expression. A manual split can help you customize the data split logic, and handle complex or non-standard data formats. A store name feature is a feature that indicates the name of the store where the sales data was collected. A store name feature can help you identify the source of the data, and group the data by store. However, using Vertex AI manual split, using the store name feature to assign one store for each set would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. You would need to write code, create and configure the ml_use label or the data filter expression, and assign one store for each set. Moreover, this option would not ensure that the data in each set has the same distribution and characteristics as the data in the whole dataset, which could prevent you from learning the general pattern of the data, and cause bias or variance in the model2.
• Option C: Using Vertex AI chronological split and specifying the sales timestamp feature as the time variable would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. A chronological split is a data split method that allows you to split your data into sets based on the order of the data. A chronological split can help you preserve the temporal dependency and sequence of the data, and avoid data leakage. A sales timestamp feature is a feature that indicates the date and time when the sales data was collected. A sales timestamp feature can help you track the changes and trends of the data over time, and capture the seasonality and cyclicality of the data. However, using Vertex AI chronological split and specifying the sales timestamp feature as the time variable would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. You would need to write code, create and configure the time variable, and split the data by the order of the time variable. Moreover, this option would not ensure that the data in each set has the same distribution and characteristics as the data in the whole dataset, which could prevent you from learning the general pattern of the data, and cause bias or variance in the model3.
• Option D: Using Vertex AI random split, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set would not allow you to use the default data split method that is provided by Vertex AI, and could increase the complexity and cost of the data split process. A random split is a data split method that allows you to split your data into sets by using a random sampling method, and assign a custom percentage of the data to each set. A random split can help you split your data into representative and balanced sets, and avoid data leakage. However, using Vertex AI random split, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set would not allow you to use the default data split method that is provided by Vertex AI, and could increase the complexity and cost of the data split process. You would need to write code, create and configure the random split method, and assign the custom percentages to each set. Moreover, this option would not use the default data split method that is provided by Vertex AI, which can simplify the data split process, and works well in most cases1.

References:

• About data splits for AutoML models | Vertex AI | Google Cloud
• Manual split for unstructured data
• Mathematical split

This answer is correct because it allows you to use the trained TensorFlow model for batch predictions on text data stored in BigQuery without any additional processing or overhead. Al Platform provides a service for running batch prediction jobs that can take input data from BigQuery or Cloud Storage and write the output to BigQuery or Cloud Storage. You can use the SavedModel format to export your TensorFlow model to Cloud Storage and then submit a batch prediction job that points to the model location and the input data location. Al Platform will handle the scaling and distribution of the prediction requests and return the results in the specified output location. References:

• [Al Platform: Batch prediction overview]
• [Al Platform: Exporting a SavedModel for prediction]

 TFX (TensorFlow Extended) is a platform for end-to-end machine learning pipelines. It provides components for data ingestion, preprocessing, validation, model training, serving, and monitoring. Dataflow is a fully managed service for scalable data processing. By using TFX components with Dataflow, you can perform feature engineering on large-scale tabular data in a distributed and efficient way. You can use the Transform component to apply the MaxMin scaler and the one-hot encoding to the numerical and categorical features, respectively. You can also use the ExampleGen component to read data from BigQuery and the Trainer component to train your TensorFlow model. The output of the Transform component is a TFRecord file, which is a binary format for storing TensorFlow data. You can export the TFRecord file to Cloud Storage and feed it into Vertex AI Training, which is a managed service for training custom machine learning models on Google Cloud. References:

• TFX | TensorFlow
• Dataflow | Google Cloud
• Vertex AI Training | Google Cloud

• Option A is incorrect because using latitude, longitude, and product type as features, and using profit as model output is not the best way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option does not capture the interaction between latitude and longitude, which may affect the profitability of the product. For example, the same product may have different profitability in different regions, depending on the climate, culture, or preferences of the customers. Moreover, this option does not account for the granularity of the location data, which may be too fine or too coarse for the model. For example, using the exact coordinates of a city may not be meaningful, as the profitability may vary within the city, or using the country name may not be informative, as the profitability may vary across the country.
• Option B is incorrect because using latitude, longitude, and product type as features, and using revenue and expenses as model outputs is not a suitable way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option has the same drawbacks as option A, as it does not capture the interaction between latitude and longitude, or account for the granularity of the location data. Moreover, this option does not directly predict the profitability of the product, which is the target variable of interest. Instead, it predicts the revenue and expenses of the product, which are intermediate variables that depend on other factors, such as the price, the cost, or the demand of the product. To obtain the profitability, we would need to subtract the expenses from the revenue, which may introduce errors or uncertainties in the prediction.
• Option C is correct because using product type and the feature cross of latitude with longitude, followed by binning, as features, and using profit as model output is a good way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option captures the interaction between latitude and longitude, which may affect the profitability of the product, by creating a feature cross of these two features. A feature cross is a synthetic feature that combines the values of two or more features into a single feature1. This option also accounts for the granularity of the location data, by binning the feature cross into discrete buckets. Binning is a technique that groups continuous values into intervals, which can reduce the noise and complexity of the data2. Moreover, this option directly predicts the profitability of the product, which is the target variable of interest, by using it as the model output.
• Option D is incorrect because using product type and the feature cross of latitude with longitude, followed by binning, as features, and using revenue and expenses as model outputs is not a valid way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option has the same advantages as option C, as it captures the interaction between latitude and longitude, and accounts for the granularity of the location data, by creating a feature cross and binning it. However, this option does not directly predict the profitability of the product, which is the target variable of interest, but rather predicts the revenue and expenses of the product, which are intermediate variables that depend on other factors, as explained in option B.

References:

• Feature cross
• Binning
• [Profitability]
• [Revenue and expenses]
• [Latitude and longitude]
• [Product type]

The best option for deploying a new version of a model to a production Vertex AI endpoint that is serving traffic, directing all user traffic to the new model, and deploying the model with minimal disruption to your application, is to create a new model, set the parentModel parameter to the model ID of the currently deployed model, upload the model to Vertex AI Model Registry, deploy the new model to the existing endpoint, and set the new model to 100% of the traffic. This option allows you to leverage the power and simplicity of Vertex AI to update your model version and serve online predictions with low latency. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can deploy a trained model to an online prediction endpoint, which can provide low-latency predictions for individual instances. A model is a resource that represents a machine learning model that you can use for prediction. A model can have one or more versions, which are different implementations of the same model. A model version can have different parameters, code, or data than another version of the same model. A model version can help you experiment and iterate on your model, and improve the model performance and accuracy. A parentModel parameter is a parameter that specifies the model ID of the model that the new model version is based on. A parentModel parameter can help you inherit the settings and metadata of the existing model, and avoid duplicating the model configuration. Vertex AI Model Registry is a service that can store and manage your machine learning models on Google Cloud. Vertex AI Model Registry can help you upload and organize your models, and track the model versions and metadata. An endpoint is a resource that provides the service endpoint (URL) you use to request the prediction. An endpoint can have one or more deployed models, which are instances of model versions that are associated with physical resources. A deployed model can help you serve online predictions with low latency, and scale up or down based on the traffic. By creating a new model, setting the parentModel parameter to the model ID of the currently deployed model, uploading the model to Vertex AI Model Registry, deploying the new model to the existing endpoint, and setting the new model to 100% of the traffic, you can deploy a new version of a model to a production Vertex AI endpoint that is serving traffic, direct all user traffic to the new model, and deploy the model with minimal disruption to your application1.

The other options are not as good as option C, for the following reasons:

• Option A: Creating a new endpoint, creating a new model, setting it as the default version, uploading the model to Vertex AI Model Registry, deploying the new model to the new endpoint, and updating Cloud DNS to point to the new endpoint would require more skills and steps than creating a new model, setting the parentModel parameter to the model ID of the currently deployed model, uploading the model to Vertex AI Model Registry, deploying the new model to the existing endpoint, and setting the new model to 100% of the traffic. Cloud DNS is a service that can provide reliable and scalable Domain Name System (DNS) services on Google Cloud. Cloud DNS can help you manage your DNS records, and resolve domain names to IP addresses. By updating Cloud DNS to point to the new endpoint, you can redirect the user traffic to the new endpoint, and avoid breaking the existing application. However, creating a new endpoint, creating a new model, setting it as the default version, uploading the model to Vertex AI Model Registry, deploying the new model to the new endpoint, and updating Cloud DNS to point to the new endpoint would require more skills and steps than creating a new model, setting the parentModel parameter to the model ID of the currently deployed model, uploading the model to Vertex AI Model Registry, deploying the new model to the existing endpoint, and setting the new model to 100% of the traffic. You would need to write code, create and configure the new endpoint, create and configure the new model, upload the model to Vertex AI Model Registry, deploy the model to the new endpoint, and update Cloud DNS to point to the new endpoint. Moreover, this option would create a new endpoint, which can increase the maintenance and management costs2.
• Option B: Creating a new endpoint, creating a new model, setting the parentModel parameter to the model ID of the currently deployed model and setting it as the default version, uploading the model to Vertex AI Model Registry, and deploying the new model to the new endpoint and setting the new model to 100% of the traffic would require more skills and steps than creating a new model, setting the parentModel parameter to the model ID of the currently deployed model, uploading the model to Vertex AI Model Registry, deploying the new model to the existing endpoint, and setting the new model to 100% of the traffic. A parentModel parameter is a parameter that specifies the model ID of the model that the new model version is based on. A parentModel parameter can help you inherit the settings and metadata of the existing model, and avoid duplicating the model configuration. A default version is a model version that is used for prediction when no other version is specified. A default version can help you simplify the prediction request, and avoid specifying the model version every time. By setting the parentModel parameter to the model ID of the currently deployed model and setting it as the default version, you can create a new model that is based on the existing model, and use it for prediction without specifying the model version. However, creating a new endpoint, creating a new model, setting the parentModel parameter to the model ID of the currently deployed model and setting it as the default version, uploading the model to Vertex AI Model Registry, and deploying the new model to the new endpoint and setting the new model to 100% of the traffic would require more skills and steps than creating a new model, setting the parentModel parameter to the model ID of the currently deployed model, uploading the model to Vertex AI Model Registry, deploying the new model to the existing endpoint, and setting the new model to 100% of the traffic. You would need to write code, create and configure the new endpoint, create and configure the new model, upload the model to Vertex AI Model Registry, and deploy the model to the new endpoint. Moreover, this option would create a new endpoint, which can increase the maintenance and management costs2.
• Option D: Creating a new model, setting it as the default version, uploading the model to Vertex AI Model Registry, and deploying the new model to the existing endpoint would not allow you to inherit the settings and metadata of the existing model, and could cause errors or poor performance. A default version is a model version that is used for prediction when no other version is specified. A default version can help you simplify the prediction request, and avoid specifying the model version every time. By setting the new model as the default version, you can use the new model for prediction without specifying the model version. However, creating a new model, setting it as the default version, uploading the model to Vertex AI Model Registry, and deploying the new model to the existing endpoint would not allow you to inherit the settings and metadata of the existing model, and could cause errors or poor performance. You would need to write code, create and configure the new model, upload the model to Vertex AI Model Registry, and deploy the model to the existing endpoint. Moreover, this option would not set the parentModel parameter to the model ID of the currently deployed model, which could prevent you from inheriting the settings and metadata of the existing model, and cause inconsistencies or conflicts between the model versions2.

References:

• Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 2: Serving ML Predictions
• Google Cloud Professional Machine Learning Engineer Exam Guide, Section 3: Scaling ML models in production, 3.1 Deploying ML models to production
• Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 6: Production ML Systems, Section 6.2: Serving ML Predictions
• Vertex AI
• Cloud DNS

 The best option for building a recommendation system without any user event data is to use simple heuristics based on content metadata. This is a type of content-based filtering, which recommends items that are similar to the ones that the user has interacted with or selected, based on their attributes. For example, if a user selects a comedy movie from the US released in 2020, the system can recommend other comedy movies from the US released in 2020 or nearby years. This approach does not require any machine learning, but it can leverage the existing metadata of the videos to provide relevant recommendations. It also allows the system to start collecting user event data, such as views, likes, ratings, etc., which can be used to train a more sophisticated machine learning model in the future, such as a collaborative filtering model or a hybrid model that combines content and collaborative information. References:

• Recommendation Systems
• Content-Based Filtering
• Collaborative Filtering
• Hybrid Recommender Systems: A Systematic Literature Review

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. TensorFlow Transform2 is a library for preprocessing data with TensorFlow. TensorFlow Transform enables you to define and execute distributed pre-processing or feature engineering functions on large data sets, and then export the same functions as a TensorFlow graph for re-use during training or serving. TensorFlow Transform can handle both instance-level and full-pass data transformations. Apache Beam3 is an open source framework for building scalable and portable data pipelines. Apache Beam supports both batch and streaming data processing. Dataflow4 is a fully managed service for running Apache Beam pipelines on Google Cloud. Dataflow handles the provisioning and management of the compute resources, as well as the optimization and execution of the pipelines. Therefore, option D is the best way to configure the preprocessing routine for the given use case, as it allows you to use the same preprocessing logic during model training and serving, and leverage the scalability and performance of Dataflow. The other options are not relevant or optimal for this scenario. References:

• Professional ML Engineer Exam Guide
• TensorFlow Transform
• Apache Beam
• Dataflow
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

The best option for scaling the training workload while minimizing cost is to package the code with Setuptools, and use a pre-built container. Train the model with Vertex AI using a custom tier that contains the required GPUs. This option has the following advantages:

• It allows the code to be easily packaged and deployed, as Setuptools is a Python tool that helps to create and distribute Python packages, and pre-built containers are Docker images that contain all the dependencies and libraries needed to run the code. By packaging the code with Setuptools, and using a pre-built container, you can avoid the hassle and complexity of building and maintaining your own custom container, and ensure the compatibility and portability of your code across different environments.
• It leverages the scalability and performance of Vertex AI, which is a fully managed service that provides various tools and features for machine learning, such as training, tuning, serving, and monitoring. By training the model with Vertex AI, you can take advantage of the distributed and parallel training capabilities of Vertex AI, which can speed up the training process and improve the model quality. Vertex AI also supports various frameworks and models, such as PyTorch and ResNet50, and allows you to use custom containers and custom tiers to customize your training configuration and resources.
• It reduces the cost and complexity of the training process, as Vertex AI allows you to use a custom tier that contains the required GPUs, which can optimize the resource utilization and allocation for your training job. By using a custom tier that contains 4 V100 GPUs, you can match the number and type of GPUs that you plan to use for your training job, and avoid paying for unnecessary or underutilized resources. Vertex AI also offers various pricing options and discounts, such as per-second billing, sustained use discounts, and preemptible VMs, that can lower the cost of the training process.

The other options are less optimal for the following reasons:

• Option A: Configuring a Compute Engine VM with all the dependencies that launches the training. Train the model with Vertex AI using a custom tier that contains the required GPUs, introduces additional complexity and overhead. This option requires creating and managing a Compute Engine VM, which is a virtual machine that runs on Google Cloud. However, using a Compute Engine VM to launch the training may not be necessary or efficient, as it requires installing and configuring all the dependencies and libraries needed to run the code, and maintaining and updating the VM. Moreover, using a Compute Engine VM to launch the training may incur additional cost and latency, as it requires paying for the VM usage and transferring the data and the code between the VM and Vertex AI.
• Option C: Creating a Vertex AI Workbench user-managed notebooks instance with 4 V100 GPUs, and using it to train the model, introduces additional cost and risk. This option requires creating and managing a Vertex AI Workbench user-managed notebooks instance, which is a service that allows you to create and run Jupyter notebooks on Google Cloud. However, using a Vertex AI Workbench user-managed notebooks instance to train the model may not be optimal or secure, as it requires paying for the notebooks instance usage, which can be expensive and wasteful, especially if the notebooks instance is not used for other purposes. Moreover, using a Vertex AI Workbench user-managed notebooks instance to train the model may expose the model and the data to potential security or privacy issues, as the notebooks instance is not fully managed by Google Cloud, and may be accessed or modified by unauthorized users or malicious actors.
• Option D: Creating a Google Kubernetes Engine cluster with a node pool that has 4 V100 GPUs. Prepare and submit a TFJob operator to this node pool, introduces additional complexity and cost. This option requires creating and managing a Google Kubernetes Engine cluster, which is a fully managed service that runs Kubernetes clusters on Google Cloud. Moreover, this option requires creating and managing a node pool that has 4 V100 GPUs, which is a group of nodes that share the same configuration and resources. Furthermore, this option requires preparing and submitting a TFJob operator to this node pool, which is a Kubernetes custom resource that defines a TensorFlow training job. However, using Google Kubernetes Engine, node pool, and TFJob operator to train the model may not be necessary or efficient, as it requires configuring and maintaining the cluster, the node pool, and the TFJob operator, and paying for their usage. Moreover, using Google Kubernetes Engine, node pool, and TFJob operator to train the model may not be compatible or scalable, as they are designed for TensorFlow models, not PyTorch models, and may not support distributed or parallel training.

References:

• [Vertex AI: Training with custom containers]
• [Vertex AI: Using custom machine types]
• [Setuptools documentation]
• [PyTorch documentation]
• [ResNet50 | PyTorch]

 Cloud Storage is a scalable and cost-effective storage service for any type of data. By storing image files in Cloud Storage, you can access them from anywhere and avoid the overhead of managing your own storage infrastructure. However, accessing image files directly from Cloud Storage can be slow and inefficient, especially for large-scale training. A better option is to use serialized records, such as TFRecord or Apache Avro, which are binary formats that store multiple images and their labels in a single file. Serialized records can improve the data throughput and reduce the network latency, as well as enable data compression and sharding. You can use TensorFlow or Apache Beam APIs to create and read serialized records from Cloud Storage. This solution requires minimal code changes and can speed up your training time significantly. References:

• Cloud Storage | Google Cloud
• TFRecord and tf.Example | TensorFlow Core
• Apache Avro 1.10.2 Specification
• Using Apache Beam with Cloud Storage | Cloud Storage

The best option for creating a Dataflow pipeline for real-time anomaly detection is to load the model directly into the Dataflow job as a dependency, and use it for prediction. This option has the following advantages:

• It minimizes the serving latency, as the model prediction logic is executed within the same Dataflow pipeline that ingests and processes the data. There is no need to invoke external services or containers, which can introduce network overhead and latency.
• It simplifies the deployment and management of the model, as the model is packaged with the Dataflow job and does not require a separate service or container. The model can be updated by redeploying the Dataflow job with a new model version.
• It leverages the scalability and reliability of Dataflow, as the model prediction logic can scale up or down with the data volume and handle failures and retries automatically.

The other options are less optimal for the following reasons:

• Option A: Containerizing the model prediction logic in Cloud Run, which is invoked by Dataflow, introduces additional latency and complexity. Cloud Run is a serverless platform that runs stateless containers, which means that the model prediction logic needs to be initialized and loaded every time a request is made. This can increase the cold start latency and reduce the throughput. Moreover, Cloud Run has a limit on the number of concurrent requests per container, which can affect the scalability of the model prediction logic. Additionally, this option requires managing two separate services: the Dataflow pipeline and the Cloud Run container.
• Option C: Deploying the model to a Vertex AI endpoint, and invoking this endpoint in the Dataflow job, also introduces additional latency and complexity. Vertex AI is a managed service that provides various tools and features for machine learning, such as training, tuning, serving, and monitoring. However, invoking a Vertex AI endpoint from a Dataflow job requires making an HTTP request, which can incur network overhead and latency. Moreover, this option requires managing two separate services: the Dataflow pipeline and the Vertex AI endpoint.
• Option D: Deploying the model in a TFServing container on Google Kubernetes Engine, and invoking it in the Dataflow job, also introduces additional latency and complexity. TFServing is a high-performance serving system for TensorFlow models, which can handle multiple versions and variants of a model. However, invoking a TFServing container from a Dataflow job requires making a gRPC or REST request, which can incur network overhead and latency. Moreover, this option requires managing two separate services: the Dataflow pipeline and the Google Kubernetes Engine cluster.

References:

• [Dataflow documentation]
• [TensorFlow documentation]
• [Cloud Run documentation]
• [Vertex AI documentation]
• [TFServing documentation]

Vertex AI Pipelines is a service that allows you to orchestrate and automate your machine learning (ML) workflows using pipelines1. A pipeline is a description of an ML workflow, including all of the components in the workflow, how the components are connected as a graph, and the runtime parameters that the pipeline accepts1. Vertex AI Pipelines helps you manage the end-to-end lifecycle of your ML projects, from data preprocessing to model deployment1.

Vertex AI Feature Store is a service that enables you to serve, share, and reuse ML features across different models and projects2. A feature is a measurable property or characteristic of an entity, such as the age of a person or the price of a product2. Vertex AI Feature Store helps you reduce data duplication, ensure data consistency, and improve model performance2.

Vertex AI Experiments is a service that helps you track and compare the performance of different versions of your models3. You can use Vertex AI Experiments to run multiple training jobs with different hyperparameters, architectures, or data sources, and then compare the results using metrics, visualizations, and reports3. Vertex AI Experiments helps you identify the best model for your use case and optimize your model performance3. References:

• Vertex AI Pipelines | Google Cloud
• Vertex AI Feature Store | Google Cloud
• Vertex AI Experiments | Google Cloud

 Hyperparameter tuning is the process of finding the optimal values for the parameters of a machine learning model that affect its performance. AI Platform provides a service for hyperparameter tuning that can run multiple trials in parallel and use different search algorithms to find the best combination of hyperparameters. However, hyperparameter tuning can be time-consuming and costly, especially if the search space is large and the model training is complex. Therefore, it is important to optimize the tuning job to reduce the time and resources required.

One way to speed up the tuning job is to set the early stopping parameter to TRUE. This means that the tuning service will automatically stop trials that are unlikely to perform well based on the intermediate results. This can save time and resources by avoiding unnecessary computations for trials that are not promising. The early stopping parameter can be set in the trainingInput.hyperparameters field of the training job request1

Another way to speed up the tuning job is to decrease the maximum number of trials during subsequent training phases. This means that the tuning service will use fewer trials to refine the search space after the initial phase. This can reduce the time required for the tuning job to converge to the optimal solution. The maximum number of trials can be set in the trainingInput.hyperparameters.maxTrials field of the training job request1

The other options are not effective ways to speed up the tuning job. Decreasing the number of parallel trials will reduce the concurrency of the tuning job and increase the overall time required. Decreasing the range of floating-point values will reduce the diversity of the search space and may miss some optimal solutions. Changing the search algorithm from Bayesian search to random search will reduce the efficiency of the tuning job and may require more trials to find the best solution1

References: 1: Hyperparameter tuning overview

According to the official exam guide1, one of the skills assessed in the exam is to “configure and optimize model monitoring jobs”. Vertex AI Model Monitoring documentation states that “model monitoring helps you detect when your model’s performance degrades over time due to changes in the data that your model receives or returns” and that "you can configure model monitoring to send notifications to Pub/Sub when it detects anomalies or drift in your model’s predictions"2. Therefore, enabling model monitoring on the Vertex AI endpoint and configuring Pub/Sub to call the Cloud Function when feature drift is detected would help you keep the model up-to-date and minimize retraining costs. The other options are not relevant or optimal for this scenario. References:

• Professional ML Engineer Exam Guide
• Vertex AI Model Monitoring
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Medical entity extraction is a task that involves identifying and classifying medical terms or concepts from unstructured textual data, such as electronic health records, clinical notes, or research papers. Medical entity extraction can help with various use cases, such as information retrieval, knowledge discovery, decision support, and data analysis1.

One possible approach to perform medical entity extraction is to use a BERT-based model to fine-tune a medical entity extraction model. BERT (Bidirectional Encoder Representations from Transformers) is a pre-trained language model that can capture the contextual information from both left and right sides of a given token2. BERT can be fine-tuned on a specific downstream task, such as medical entity extraction, by adding a task-specific layer on top of the pre-trained model and updating the model parameters with a small amount of labeled data3.

A BERT-based model can achieve high performance on medical entity extraction by leveraging the large-scale pre-training on general-domain corpora and the fine-tuning on domain-specific data. For example, Nesterov and Umerenkov4 proposed a novel method of doing medical entity extraction from electronic health records as a single-step multi-label classification task by fine-tuning a transformer model pre-trained on a large EHR dataset. They showed that their model can achieve human-level quality for most frequent entities.

References:

• 1: Medical Named Entity Recognition from Un-labelled Medical Records based on Pre-trained Language Models and Domain Dictionary | Data Intelligence | MIT Press
• 2: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• 3: Fine-tuning BERT for Medical Entity Extraction
• 4: Distantly supervised end-to-end medical entity extraction from electronic health records with human-level quality

 Recommendations AI is a service that allows users to build, test, and deploy personalized product recommendations for their ecommerce websites. It uses Google’s deep learning models to learn from user behavior and product data, and generate high-quality recommendations that can increase revenue, click-through rate, and customer satisfaction. One of the best practices for using Recommendations AI is to choose the right recommendation type for the business objective. The “Frequently Bought Together” recommendation type shows products that are often purchased together with the current product, and encourages users to add more items to their shopping cart. This can increase the average order value and the revenue for each transaction. The other options are not as effective or feasible for this objective. The “Other Products You May Like” recommendation type shows products that are similar to the current product, and may increase the click-through rate, but not necessarily the shopping cart size. Importing the user events and then the product catalog is not a recommended order, as it may cause data inconsistency and missing recommendations. The product catalog should be imported first, and then the user events. Using placeholder values for the product catalog is not a viable option, as it will not produce meaningful recommendations or reflect the real performance of the model. References:

• Recommendations AI documentation
• Choosing a recommendation type
• Importing data to Recommendations AI

The best option for using a managed service to submit training jobs with different frameworks is to use Vertex AI Training. Vertex AI Training is a fully managed service that allows you to train custom models on Google Cloud using any framework, such as TensorFlow, PyTorch, scikit-learn, XGBoost, etc. You can also use custom containers to run your own libraries and dependencies. Vertex AI Training handles the infrastructure provisioning, scaling, and monitoring for you, so you can focus on your model development and optimization. Vertex AI Training also integrates with other Vertex AI services, such as Vertex AI Pipelines, Vertex AI Experiments, and Vertex AI Prediction. The other options are not as suitable for using a managed service to submit training jobs with different frameworks, because:

• Configuring Kubeflow to run on Google Kubernetes Engine and submit training jobs through TFJob would require more infrastructure maintenance, as Kubeflow is not a fully managed service, and you would have to provision and manage your own Kubernetes cluster. This would also incur more costs, as you would have to pay for the cluster resources, regardless of the training job usage. TFJob is also mainly designed for TensorFlow models, and might not support other frameworks as well as Vertex AI Training.
• Creating a library of VM images on Compute Engine, and publishing these images on a centralized repository would require more development time and effort, as you would have to create and maintain different VM images for different frameworks and libraries. You would also have to manually configure and launch the VMs for each training job, and handle the scaling and monitoring yourself. This would not leverage the benefits of a managed service, such as Vertex AI Training.
• Setting up Slurm workload manager to receive jobs that can be scheduled to run on your cloud infrastructure would require more configuration and administration, as Slurm is not a native Google Cloud service, and you would have to install and manage it on your own VMs or clusters. Slurm is also a general-purpose workload manager, and might not have the same level of integration and optimization for ML frameworks and libraries as Vertex AI Training. References:
• Vertex AI Training | Google Cloud
• Kubeflow on Google Cloud | Google Cloud
• TFJob for training TensorFlow models with Kubernetes | Kubeflow
• Compute Engine | Google Cloud
• Slurm Workload Manager

Data Catalog is a fully managed and scalable metadata management service that allows you to quickly discover, manage, and understand your data in Google Cloud. You can use Data Catalog to search the BigQuery datasets by using keywords in the table description, as well as other metadata attributes such as table name, column name, labels, tags, and more. Data Catalog also provides a rich browsing experience that lets you explore the schema, preview the data, and access the BigQuery console directly from the Data Catalog UI. Data Catalog helps you find the data that you need for your model building on AI Platform without writing any code or queries.

References:

• [Data Catalog documentation]
• [Data Catalog overview]
• [Searching for data assets]

When you deploy a custom container to Vertex AI Model Registry, you need to follow some requirements for the container configuration. One of these requirements is to use the HTTP port 8080 for serving predictions. If you use a different port, the model server might not be able to communicate with Vertex AI and cause the error “Error model server never became ready”. To fix this error, you need to change the HTTP port in your model’s configuration to the default value of 8080 and redeploy the container. References:

• Custom container requirements documentation
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. Document AI2 is a document understanding platform that takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume. Document AI Workbench3 allows you to create custom extractors to parse the text in specific sections of your documents. Natural Language API4 is a service that provides natural language understanding technologies, such as sentiment analysis, entity analysis, and other text annotations. The analyzeSentiment feature5 inspects the given text and identifies the prevailing emotional opinion within the text, especially to determine a writer’s attitude as positive, negative, or neutral. Therefore, option C is the best way to accomplish the task of predicting an overall satisfaction score from the customer comments on each form. The other options are not relevant or optimal for this scenario. References:

• Professional ML Engineer Exam Guide
• Document AI
• Document AI Workbench
• Natural Language API
• Sentiment analysis
• Google Professional Machine Learning Certification Exam 2023
• Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

 Vertex AI is a service that allows you to create and train ML models using Google Cloud technologies. You can use Vertex AI to import the model that you trained with TensorFlow and store it in the Vertex AI Model Registry. The Vertex AI Model Registry is a service that allows you to store and manage your ML models on Google Cloud. You can then use Vertex AI Pipelines to create a pipeline that uses the DataflowPythonJobOp and the ModelBatchPredictOp components. The DataflowPythonJobOp component is a component that allows you to run a Dataflow job using a Python script. Dataflow is a service that allows you to create and run scalable and portable data processing pipelines on Google Cloud. You can use the DataflowPythonJobOp component to reuse the data processing logic that you created for transforming the data into TFRecords. The ModelBatchPredictOp component is a component that allows you to run a batch prediction job using a model from the Vertex AI Model Registry. Batch prediction is a type of prediction that provides high-throughput responses to large batches of input data. You can use the ModelBatchPredictOp component to make predictions using the TFRecords from the DataflowPythonJobOp component and the model from the Vertex AI Model Registry. You can also configure the ModelBatchPredictOp component to automatically upload the predictions to a BigQuery table. BigQuery is a service that allows you to store and query large amounts of data in a scalable and cost-effective way. You can use BigQuery to store and analyze the predictions from your model. You can also schedule the pipeline to run on a weekly basis, so that the predictions are updated regularly. By using Vertex AI, Vertex AI Pipelines, Dataflow, and BigQuery, you can productionize the model and upload the predictions to a BigQuery table on a weekly schedule. References:

• Vertex AI documentation
• Vertex AI Pipelines documentation
• Dataflow documentation
• BigQuery documentation
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

 Vertex AI Experiments is a service that allows you to track, compare, and manage experiments with Vertex AI. You can use Vertex AI Experiments to record the parameters, metrics, and artifacts of each model training run, and compare them in a graphical interface. Vertex AI Experiments supports models trained in Vertex AI Pipelines, Vertex AI Custom Training, and Vertex AI Workbench notebooks. To use Vertex AI Experiments, you need to create an experiment and submit your pipeline runs or custom training jobs as experiment runs. For models trained on notebooks, you need to use the Vertex AI SDK to log the parameters and metrics to the experiment. This way, you can minimize the effort required to store and compare the model performance across different services. References: Track, compare, manage experiments with Vertex AI Experiments, Vertex AI Pipelines: Metrics visualization and run comparison using the KFP SDK, [Vertex AI SDK for Python]

The best approach to build a model that predicts how much inventory the logistics team should order each month is to use a time series forecasting model to predict each item’s monthly sales. This approach can capture the temporal patterns and trends in the sales data, such as seasonality, cyclicality, and autocorrelation. It can also account for the variability and uncertainty in the demand, and provide confidence intervals and error metrics for the predictions. By using a time series forecasting model, you can provide the logistics team with accurate and reliable estimates of the future sales for each item, which can help them optimize the inventory levels and avoid overstocking or understocking. You can use various methods and tools to build a time series forecasting model, such as ARIMA, LSTM, Prophet, or BigQuery ML.

The other options are not optimal for the following reasons:

• A. Using a clustering algorithm to group popular items together is not a good approach, as it does not provide any quantitative or temporal information about the sales or the inventory. It only provides a qualitative and static categorization of the items based on their similarity or dissimilarity. Moreover, clustering is an unsupervised learning technique, which does not use any target variable or feedback to guide the learning process. This can result in arbitrary and inconsistent clusters, which may not reflect the true demand or preferences of the customers.
• B. Using a regression model to predict how much additional inventory should be purchased each month is not a good approach, as it does not account for the individual differences and dynamics of each item. It only provides a single aggregated value for the whole inventory, which can be misleading and inaccurate. Moreover, a regression model is not well-suited for handling time series data, as it assumes that the data points are independent and identically distributed, which is not the case for sales data. A regression model can also suffer from overfitting or underfitting, depending on the choice and complexity of the features and the model.
• D. Using a classification model to classify inventory levels as UNDER_STOCKED, OVER_STOCKED, and CORRECTLY_STOCKED is not a good approach, as it does not provide any numerical or predictive information about the sales or the inventory. It only provides a discrete and subjective label for the inventory levels, which can be vague and ambiguous. Moreover, a classification model is not well-suited for handling time series data, as it assumes that the data points are independent and identically distributed, which is not the case for sales data. A classification model can also suffer from class imbalance, misclassification, or overfitting, depending on the choice and complexity of the features, the model, and the threshold.

References:

• Professional ML Engineer Exam Guide
• Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate
• Google Cloud launches machine learning engineer certification
• Time Series Forecasting: Principles and Practice
• BigQuery ML: Time series analysis

The best option for reducing pipeline execution time and cost, while also minimizing pipeline changes, is to enable caching for the pipeline job, and disable caching for the model training step. This option allows you to leverage the power and simplicity of Vertex AI Pipelines to reuse the output of the data preprocessing step, and avoid unnecessary recomputation. Vertex AI Pipelines is a service that can orchestrate machine learning workflows using Vertex AI. Vertex AI Pipelines can run preprocessing and training steps on custom Docker images, and evaluate, deploy, and monitor the machine learning model. Caching is a feature of Vertex AI Pipelines that can store and reuse the output of a pipeline step, and skip the execution of the step if the input parameters and the code have not changed. Caching can help you reduce the pipeline execution time and cost, as you do not need to re-run the same step with the same input and code. Caching can also help you minimize the pipeline changes, as you do not need to add or remove any pipeline steps or parameters. By enabling caching for the pipeline job, and disabling caching for the model training step, you can create a Vertex AI pipeline that includes two steps. The first step preprocesses 10 TB data, completes in about 1 hour, and saves the result in a Cloud Storage bucket. The second step uses the processed data to train a model. You can update the model’s code to allow you to test different algorithms, and run the pipeline job with caching enabled. The pipeline job will reuse the output of the data preprocessing step from the cache, and skip the execution of the step. The pipeline job will run the model training step with the updated code, and disable the caching for the step. This way, you can reduce the pipeline execution time and cost, while also minimizing pipeline changes1.

The other options are not as good as option D, for the following reasons:

• Option A: Adding a pipeline parameter and an additional pipeline step, depending on the parameter value, the pipeline step conducts or skips data preprocessing and starts model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. A pipeline parameter is a variable that can be used to control the input or output of a pipeline step. A pipeline parameter can help you customize the pipeline logic and behavior, and experiment with different values. An additional pipeline step is a new instance of a pipeline component that can perform a part of the pipeline workflow, such as data preprocessing or model training. An additional pipeline step can help you extend the pipeline functionality and complexity, and handle different scenarios. However, adding a pipeline parameter and an additional pipeline step, depending on the parameter value, the pipeline step conducts or skips data preprocessing and starts model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. You would need to write code, define the pipeline parameter, create the additional pipeline step, implement the conditional logic, and compile and run the pipeline. Moreover, this option would not reuse the output of the data preprocessing step from the cache, but rather from the Cloud Storage bucket, which can increase the data transfer and access costs1.
• Option B: Creating another pipeline without the preprocessing step, and hardcoding the preprocessed Cloud Storage file location for model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. A pipeline without the preprocessing step is a pipeline that only includes the model training step, and uses the preprocessed data from the Cloud Storage bucket as the input. A pipeline without the preprocessing step can help you avoid running the data preprocessing step every time, and reduce the pipeline execution time and cost. However, creating another pipeline without the preprocessing step, and hardcoding the preprocessed Cloud Storage file location for model training, would require more skills and steps than enabling caching for the pipeline job, and disabling caching for the model training step. You would need to write code, create a new pipeline, remove the preprocessing step, hardcode the Cloud Storage file location, and compile and run the pipeline. Moreover, this option would not reuse the output of the data preprocessing step from the cache, but rather from the Cloud Storage bucket, which can increase the data transfer and access costs. Furthermore, this option would create another pipeline, which can increase the maintenance and management costs1.
• Option C: Configuring a machine with more CPU and RAM from the compute-optimized machine family for the data preprocessing step, would not reduce the pipeline execution time and cost, while also minimizing pipeline changes, but rather increase the pipeline execution cost and complexity. A machine with more CPU and RAM from the compute-optimized machine family is a virtual machine that has a high ratio of CPU cores to memory, and can provide high performance and scalability for compute-intensive workloads. A machine with more CPU and RAM from the compute-optimized machine family can help you optimize the data preprocessing step, and reduce the pipeline execution time. However, configuring a machine with more CPU and RAM from the compute-optimized machine family for the data preprocessing step, would not reduce the pipeline execution time and cost, while also minimizing pipeline changes, but rather increase the pipeline execution cost and complexity. You would need to write code, configure the machine type parameters for the data preprocessing step, and compile and run the pipeline. Moreover, this option would increase the pipeline execution cost, as machines with more CPU and RAM from the compute-optimized machine family are more expensive than machines with less CPU and RAM from other machine families. Furthermore, this option would not reuse the output of the data preprocessing step from the cache, but rather re-run the data preprocessing step every time, which can increase the pipeline execution time and cost1.

References:

• Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 3: MLOps
• Google Cloud Professional Machine Learning Engineer Exam Guide, Section 3: Scaling ML models in production, 3.2 Automating ML workflows
• Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 6: Production ML Systems, Section 6.4: Automating ML Workflows
• Vertex AI Pipelines
• Caching
• Pipeline parameters
• Machine types

A ResourceExhaustedError: out of memory (OOM) when allocating tensor is an error that occurs when the GPU runs out of memory while trying to allocate memory for a tensor. A tensor is a multi-dimensional array of numbers that represents the data or the parameters of a machine learning model. The size and shape of a tensor depend on various factors, such as the input data, the model architecture, the batch size, and the optimization algorithm1.

For the use case of training a computer vision model that predicts the type of government ID present in a given image using a GPU-powered virtual machine on Compute Engine, the best option to resolve the error is to reduce the batch size. The batch size is a parameter that determines how many input examples are processed at a time by the model. A larger batch size can improve the model’s accuracy and stability, but it also requires more memory and computation. A smaller batch size can reduce the memory and computation requirements, but it may also affect the model’s performance and convergence2.

By reducing the batch size, the GPU can allocate less memory for each tensor, and avoid running out of memory. Reducing the batch size can also speed up the training process, as the GPU can process more batches in parallel. However, reducing the batch size too much may also have some drawbacks, such as increasing the noise and variance of the gradient updates, and slowing down the convergence of the model. Therefore, the optimal batch size should be chosen based on the trade-off between memory, computation, and performance3.

The other options are not as effective as option B, because they are not directly related to the memory allocation of the GPU. Option A, changing the optimizer, may affect the speed and quality of the optimization process, but it may not reduce the memory usage of the model. Option C, changing the learning rate, may affect the convergence and stability of the model, but it may not reduce the memory usage of the model. Option D, reducing the image shape, may reduce the size of the input tensor, but it may also reduce the quality and resolution of the image, and affect the model’s accuracy. Therefore, option B, reducing the batch size, is the best answer for this question.

References:

• ResourceExhaustedError: OOM when allocating tensor with shape - Stack Overflow
• How does batch size affect model performance and training time? - Stack Overflow
• How to choose an optimal batch size for training a neural network? - Stack Overflow

AutoML Natural Language is a service that allows you to quickly build, test and deploy natural language processing (NLP) models without needing to have expertise in NLP or machine learning. You can use it to train a classifier on your corpus of written support cases, and then use the AutoML API to perform classification on new requests. Once the model is trained, it can be deployed as a REST API. This allows the classifier to be integrated into your pipeline and be easily consumed by other systems.

The best option for reducing the sensitivity of the dataset before training the model is to use the Cloud Data Loss Prevention (DLP) API to scan for sensitive data, and use Dataflow with the DLP API to encrypt sensitive values with Format Preserving Encryption. This option allows you to keep every column in the dataset, while protecting the sensitive data from unauthorized access or exposure. The Cloud DLP API can detect and classify various types of sensitive data, such as names, email addresses, phone numbers, credit card numbers, and more1. Dataflow can create scalable and reliable pipelines to process large volumes of data from BigQuery and other sources2. Format Preserving Encryption (FPE) is a technique that encrypts sensitive data while preserving its original format and length, which can help maintain the utility and validity of the data3. By using Dataflow with the DLP API, you can apply FPE to the sensitive values in the dataset, and store the encrypted data in BigQuery or another destination. You can also use the same pipeline to decrypt the data when needed, by using the same encryption key and method4.

The other options are not as suitable as option B, for the following reasons:

• Option A: Using Dataflow to ingest the columns with sensitive data from BigQuery, and then randomize the values in each sensitive column, would reduce the sensitivity of the data, but also the utility and accuracy of the data. Randomization is a technique that replaces sensitive data with random values, which can prevent re-identification of the data, but also distort the distribution and relationships of the data3. This can affect the performance and quality of the ML model, especially if every column is critical to the model.
• Option C: Using the Cloud DLP API to scan for sensitive data, and use Dataflow to replace all sensitive data by using the encryption algorithm AES-256 with a salt, would reduce the sensitivity of the data, but also the utility and validity of the data. AES-256 is a symmetric encryption algorithm that uses a 256-bit key to encrypt and decrypt data. A salt is a random value that is added to the data before encryption, to increase the randomness and security of the encrypted data. However, AES-256 does not preserve the format or length of the original data, which can cause problems when storing or processing the data. For example, if the original data is a 10-digit phone number, AES-256 would produce a much longer and different string, which can break the schema or logic of the dataset3.
• Option D: Before training, using BigQuery to select only the columns that do not contain sensitive data, and creating an authorized view of the data so that sensitive values cannot be accessed by unauthorized individuals, would reduce the exposure of the sensitive data, but also the completeness and relevance of the data. An authorized view is a BigQuery view that allows you to share query results with particular users or groups, without giving them access to the underlying tables. However, this option assumes that you can identify the columns that do not contain sensitive data, which may not be easy or accurate. Moreover, this option would remove some columns from the dataset, which can affect the performance and quality of the ML model, especially if every column is critical to the model.

References:

• Preparing for Google Cloud Certification: Machine Learning Engineer, Course 5: Responsible AI, Week 2: Privacy
• Google Cloud Professional Machine Learning Engineer Exam Guide, Section 5: Developing responsible AI solutions, 5.2 Implementing privacy techniques
• Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 9: Responsible AI, Section 9.4: Privacy
• De-identification techniques
• Cloud Data Loss Prevention (DLP) API
• Dataflow
• Using Dataflow and Sensitive Data Protection to securely tokenize and import data from a relational database to BigQuery
• [AES encryption]
• [Salt (cryptography)]
• [Authorized views]

• TFX ModelValidator is a tool that allows you to compare new models against a baseline model and evaluate their performance on different metrics and data slices1. You can use this tool to validate your models before deploying them to production and ensure that they meet your expectations and requirements.
• k-fold cross-validation is a technique that splits the data into k subsets and trains the model on k-1 subsets while testing it on the remaining subset. This is repeated k times and the average performance is reported2. This technique is useful for estimating the generalization error of a model, but it does not account for the dynamic nature of customer behavior or the potential changes in data distribution over time.
• Using the last relevant week of data as a validation set is a simple way to check the model’s performance on recent data, but it may not be representative of the entire data or capture the long-term trends and patterns. It also does not allow you to compare the model with a baseline or evaluate it on different data slices.
• Using the entire dataset and treating the AUC ROC as the main metric is not a good practice because it does not leave any data for validation or testing. It also assumes that the AUC ROC is the only metric that matters, which may not be true for your business problem. You may want to consider other metrics such as precision, recall, or revenue.

• Quantization is a technique that reduces the numerical precision of the weights and activations of a neural network, which can improve the inference speed and reduce the memory footprint of the model1.
• Reducing the floating point precision from tf.float64 to tf.float16 can potentially halve the latency and memory usage of the model, while having minimal impact on the accuracy2.
• Increasing the dropout rate to 0.8 in either mode would not affect the latency, but would likely degrade the performance of the model significantly, as dropout is a regularization technique that randomly drops out units during training to prevent overfitting3.
• Switching from CPU to GPU serving may or may not improve the latency, depending on the hardware specifications and the model complexity, but it would also incur additional costs and complexity for deployment4

 AutoML Tables is a service that allows you to automatically build, analyze, and deploy machine learning models on tabular data. It is suitable for large-scale regression and classification problems, and it supports various optimization objectives, data splitting methods, and hyperparameter tuning algorithms. AutoML Tables can handle both categorical and numerical features, and it can also handle missing values and outliers. AutoML Tables is a good choice for this problem because it minimizes the effort and training time required to train a regression model, while maximizing the model performance.

RMSLE stands for Root Mean Squared Logarithmic Error, and it is a metric that measures the average difference between the logarithm of the predicted values and the logarithm of the actual values. RMSLE is useful for regression problems where the target variable can include negative values, and where large differences between small values are more important than large differences between large values. For example, RMSLE penalizes underestimating a value of 10 by 2 more than overestimating a value of 1000 by 20. RMSLE is a good optimization objective for this problem because it can handle negative values in the target variable, and it can reduce the impact of outliers and large errors.

For more information about AutoML Tables and RMSLE, see the following references:

• AutoML Tables: end-to-end workflows on AI Platform Pipelines
• Predict workload failures before they happen with AutoML Tables
• How to Calculate RMSE in R

• Reasoning: The question asks for a design that serves asynchronous predictions to determine whether a machine part will fail. This means that the predictions do not need to be returned immediately to the sensors, but can be processed in batches and sent to a downstream system for monitoring. Option B is the only one that uses a streaming data pipeline with Pub/Sub and Dataflow, which can handle real-time data ingestion, processing, and prediction. Option B also invokes the model for prediction, which is required by the question. The other options either use synchronous predictions (option A), batch predictions (options C and D), or do not invoke the model for prediction (option D).
• References: You can learn more about the differences between synchronous, asynchronous, and batch predictions in Vertex AI from this document. You can also find examples of how to use Pub/Sub and Dataflow for streaming data pipelines from this tutorial and this codelab.

 The best option for performing hyperparameter tuning on Vertex AI to determine the appropriate embedding dimension and the optimal learning rate is to use UNIT_LINEAR_SCALE for the embedding dimension, UNIT_LOG_SCALE for the learning rate, and a large number of parallel trials. This option has the following advantages:

• It matches the appropriate scaling type for each hyperparameter, based on their range and distribution. The embedding dimension is an integer hyperparameter that varies linearly between 16 and 64, so using UNIT_LINEAR_SCALE makes sense. The learning rate is a double hyperparameter that varies exponentially between 10e-05 and 10e-02, so using UNIT_LOG_SCALE is more suitable.
• It maximizes the exploration of the hyperparameter space, by using a large number of parallel trials. Since training time is not a concern, using more trials can help find the best combination of hyperparameters that maximizes model accuracy. The default Bayesian optimization tuning algorithm can efficiently sample the hyperparameter space and converge to the optimal values.

The other options are less optimal for the following reasons:

• Option B: Using UNIT_LINEAR_SCALE for the embedding dimension, UNIT_LOG_SCALE for the learning rate, and a small number of parallel trials, reduces the exploration of the hyperparameter space, by using a small number of parallel trials. Since training time is not a concern, using fewer trials can miss some potentially good combinations of hyperparameters that maximize model accuracy. The default Bayesian optimization tuning algorithm can benefit from more trials to sample the hyperparameter space and converge to the optimal values.
• Option C: Using UNIT_LOG_SCALE for the embedding dimension, UNIT_LINEAR_SCALE for the learning rate, and a large number of parallel trials, mismatches the appropriate scaling type for each hyperparameter, based on their range and distribution. The embedding dimension is an integer hyperparameter that varies linearly between 16 and 64, so using UNIT_LOG_SCALE is not suitable. The learning rate is a double hyperparameter that varies exponentially between 10e-05 and 10e-02, so using UNIT_LINEAR_SCALE makes less sense.
• Option D: Using UNIT_LOG_SCALE for the embedding dimension, UNIT_LINEAR_SCALE for the learning rate, and a small number of parallel trials, combines the drawbacks of option B and option C. It mismatches the appropriate scaling type for each hyperparameter, based on their range and distribution, and reduces the exploration of the hyperparameter space, by using a small number of parallel trials.

References:

• [Vertex AI: Hyperparameter tuning overview]
• [Vertex AI: Configuring the hyperparameter tuning job]