You have recently trained an XGBoost model that you intend to deploy for online inference in production. Before sending a predict request to your model's binary, you need to perform a straightforward data preprocessing step. This step should expose a REST API that can accept requests within your internal VPC Service Controls and return predictions. Your goal is to configure this preprocessing step while minimizing both cost and effort. What should you do?
#42
You have developed a model trained on data stored in Parquet files, which are accessed through a Hive table hosted on Google Cloud. You performed data preprocessing using PySpark and exported it as a CSV file to Cloud Storage. Following preprocessing, you conducted further steps for model training and evaluation. Now, you intend to parameterize the model training process within Kubeflow Pipelines. What steps should you take to achieve this?
#43
To perform multiple classifications on various structured datasets stored in BigQuery, you aim to execute these steps without coding: exploratory data analysis, feature selection, model construction, training, hyperparameter tuning, and deployment. What is the recommended approach?
#44
You need to use TensorFlow to train an image classification model. Your dataset is located in a Cloud Storage directory and contains millions of labeled images. Before training the model, you need to prepare the data. You want the data preprocessing and model training workflow to be as efficient, scalable, and low maintenance as possible. What should you do?
#45
You work as an analyst at a large banking firm. You are developing a robust, scalable ML pipeline to train several regression and classification models. Your primary focus for the pipeline is model interpretability, and you want to quickly put the pipeline into production. What should you do?
#46
You recently used BigQuery ML to train an Vertex AI AutoML regression model. You shared the results with your team and received positive feedback. You need to deploy your model for online prediction as quickly as possible. What should you do?
#47
You've recently implemented a pipeline within Vertex AI Pipelines, which is responsible for training and deploying a model to a Vertex AI endpoint to serve real-time traffic. Your objective is to maintain an ongoing process of experimentation and iteration to enhance model performance. To facilitate this, you intend to employ Cloud Build for continuous integration and continuous deployment (CI/CD). Your ultimate goal is to efficiently and swiftly deploy new pipelines into production while minimizing the risk of potential disruptions to the existing production environment due to new pipeline implementations. What step should you take to achieve this?
#48
You work with a team of researchers to develop state-of-the-art algorithms for financial analysis. Your team develops and debugs complex models in TensorFlow. You want to maintain the ease of debugging while also reducing the model training time. How should you set up your training environment?
#49
You have developed a BigQuery ML model that predicts customer chum, and deployed the model to Vertex AI Endpoints. You want to automate the retraining of your model by using minimal additional code when model feature values change. You also want to minimize the number of times that your model is retrained to reduce training costs. What should you do?
#50
You work at a mobile gaming startup that creates online multiplayer games. Recently, your company observed an increase in players cheating in the games, leading to a loss of revenue and a poor user experience. You build a binary classification model to determine whether a player cheated after a completed game session and then send a message to other downstream systems to ban the player that cheated. Your model has performed well during testing, and you now need to deploy the model to production. You want your serving solution to provide immediate classifications after a completed game session to avoid further loss of revenue. What should you do?
#51
You have built a custom model that performs several memory-intensive preprocessing tasks before it makes a prediction. You deployed the model to a Vertex AI endpoint, and validated that results were received in a reasonable amount of time. After routing user traffic to the endpoint, you discover that the endpoint does not autoscale as expected when receiving multiple requests. What should you do?
#522 つ選択
You are using AI Platform and TPUs to train a ResNet model for categorizing different defect types in automobile engines. After capturing the training profile with the Cloud TPU profiler plugin, you notice that the process is significantly input-bound. To alleviate this bottleneck and accelerate the training, which two modifications should you consider for the tf.data dataset? (Choose two options)
#53
You work for a bank. You have been asked to develop an ML model that will support loan application decisions. You need to determine which Vertex AI services to include in the workflow. You want to track the model’s training parameters and the metrics per training epoch. You plan to compare the performance of each version of the model to determine the best model based on your chosen metrics. Which Vertex AI services should you use?
#54
You are in the process of constructing an ML model to forecast stock market trends, considering a broad spectrum of factors. During your data analysis, you observe that certain features exhibit a substantial range. To prevent these high-magnitude features from causing overfitting in the model, what action should you take?
#55
You are training a computer vision model to identify the type of government ID in images, using a GPU-powered virtual machine on Google Compute Engine. The training parameters include: - Optimizer: SGD, - Image shape: 224x224, - Batch size: 64, - Epochs: 10, - Verbose: 2. However, you encounter a ResourceExhaustedError: Out Of Memory (OOM) when allocating tensor during training. What steps should you take to resolve this issue?
#56
As an ML engineer working in the contact center of a large enterprise, your task is to develop a sentiment analysis tool for predicting customer sentiment based on recorded phone conversations. You need to determine the optimal approach to build this model while ensuring that factors such as the gender, age, and cultural differences of the customers who contacted the contact center do not influence any stage of the model development pipeline or its outcomes. What steps should you take to address this challenge?
#57
You are currently involved in the development of a system log anomaly detection model for a cybersecurity organization. This model, built with TensorFlow, is intended for real-time prediction. To facilitate this, you're tasked with setting up a Dataflow pipeline for data ingestion via Pub/Sub and subsequent storage of results in BigQuery. Your primary objective is to minimize serving latency. What steps should you take to achieve this goal?
#58
You are developing an ML model to identify your company’s products in images. You have access to over one million images in a Cloud Storage bucket. You plan to experiment with different TensorFlow models by using Vertex AI Training. You need to read images at scale during training while minimizing data I/O bottlenecks. What should you do?
#59
You work for an online grocery store. You recently developed a custom ML model that recommends a recipe when a user arrives at the website. You chose the machine type on the Vertex AI endpoint to optimize costs by using the queries per second (QPS) that the model can serve, and you deployed it on a single machine with 8 vCPUs and no accelerators. A holiday season is approaching and you anticipate four times more traffic during this time than the typical daily traffic. You need to ensure that the model can scale efficiently to the increased demand. What should you do?
#60
Your work for a textile manufacturing company. Your company has hundreds of machines, and each machine has many sensors. Your team used the sensory data to build hundreds of ML models that detect machine anomalies. Models are retrained daily, and you need to deploy these models in a cost-effective way. The models must operate 24/7 without downtime and make sub-millisecond predictions. What should you do?
