Choose Professional-Machine-Learning-Engineer most accurate study material

You work for a financial company that has a large custom dataset with one trillion tokens. The dataset contains financial news, reports, and other related data as well as acquired large public datasets similar to Common Crawl. You need to train a custom LLM from scratch using the open- source open language model (OLMo) framework. You want to maximize throughput. What should you do?

• A. Store the dataset in Filestore, and create a GKE cluster with a4-highgpu-8g machines (using B200 GPUs). Wrap your PyTorch workflow as a Google Kubernetes Engine (GKE) job that you schedule on the cluster.
• B. Store the dataset in Filestore, and mount it as NFS. Run an Agent Platform custom training job on B200 GPUs that is based on a PyTorch job.
• C. Store the dataset in Cloud Storage, and create a Google Kubernetes Engine (GKE) cluster using preemptible VMs with a4-highgpu-8g machines (using B200 GPUs). Schedule a PyTorch training job on the cluster.
• D. Buy a reservation for B200 GPUs. Use Managed Lustre to store the data, and use Cluster Toolkit to create a Slurm cluster with a4-highgpu-8g machines (using B200 GPUs). Schedule a PyTorch training job on this cluster.

You are building a real-time prediction engine that streams files which may contain Personally Identifiable Information (PII) to Google Cloud. You want to use the Cloud Data Loss Prevention (DLP) API to scan the files. How should you ensure that the PII is not accessible by unauthorized individuals?

• A. Create two buckets of data: Sensitive and Non-sensitive.
  Write all data to the Non-sensitive bucket.
  Periodically conduct a bulk scan of that bucket using the DLP API, and move the sensitive data to the Sensitive bucket.
• B. Create three buckets of data: Quarantine, Sensitive, and Non-sensitive.
  Write all data to the Quarantine bucket.
  Periodically conduct a bulk scan of that bucket using the DLP API, and move the data to either the Sensitive or Non-Sensitive bucket.
• C. Stream all files to Google Cloud, and write batches of the data to BigQuery.
  While the data is being written to BigQuery, conduct a bulk scan of the data using the DLP API.
• D. Stream all files to Google Cloud, and then write the data to BigQuery.
  Periodically conduct a bulk scan of the table using the DLP API.

You are developing a process for training and running your custom model in production. You need to be able to show lineage for your model and predictions. What should you do?

• A. 1. Use Vertex AI Experiments to train your model.
  2. Register your model in Vertex AI Model Registry.
  3. Generate batch predictions in Vertex AI.
• B. 1. Use a Vertex AI Pipelines custom training job component to tram your model.
  2. Generate predictions by using a Vertex AI Pipelines model batch predict component.
• C. 1. Upload your dataset to BigQuery.
  2. Use a Vertex AI custom training job to train your model.
  3. Generate predictions by using Vertex Al SDK custom prediction routines.
• D. 1. Create a Vertex AI managed dataset.
  2. Use a Vertex AI training pipeline to train your model.
  3. Generate batch predictions in Vertex AI.

You need to train 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. You use the following parameters:
- Optimizer: SGD
- Image shape = 224-224
- Batch size = 64
- Epochs = 10
- Verbose =2
During training you encounter the following error: ResourceExhaustedError: Out Of Memory (OOM) when allocating tensor. What should you do?

• A. Change the learning rate.
• B. Change the optimizer.
• C. Reduce the batch size.
• D. Reduce the image shape.

You are an ML engineer on an agricultural research team working on a crop disease detection tool to detect leaf rust spots in images of crops to determine the presence of a disease. These spots, which can vary in shape and size, are correlated to the severity of the disease. You want to develop a solution that predicts the presence and severity of the disease with high accuracy.
What should you do?

• A. Develop an image classification ML model to predict the presence of the disease.
• B. Develop a template matching algorithm using traditional computer vision libraries.
• C. Create an object detection model that can localize the rust spots.
• D. Develop an image segmentation ML model to locate the boundaries of the rust spots.