MLS-C01 Machine Learning Implementation and Operations Practice Test 6 — 15 Questions

Question 1

A company is using Amazon SageMaker to train a model and wants to automatically retrain the model every week using new data. Which AWS service should be used to orchestrate the retraining pipeline?

Accepted Answer

AWS Step Functions. AWS Step Functions is the recommended service for orchestrating complex workflows, including SageMaker training jobs, model creation, and deployment. Lambda is for short functions. CloudWatch Events can trigger on a schedule but not orchestrate a pipeline. Data Pipeline is older and less flexible. S3 Events trigger on object creation but not scheduling.

Answer

Amazon CloudWatch Events

Answer

AWS Lambda

Answer

AWS Data Pipeline

Question 2

A machine learning team is using SageMaker to train a model. The training data is stored in an S3 bucket encrypted with AWS KMS. The training job fails with an 'AccessDenied' error. Which IAM permission is MOST likely missing from the SageMaker execution role?

Accepted Answer

kms:Decrypt. SageMaker needs kms:Decrypt permission to read encrypted data from S3. The s3:GetObject permission is also needed, but the error specifically for encrypted data often points to missing KMS permissions. s3:ListBucket is for listing, not reading. kms:GenerateDataKey is for writing. kms:Encrypt is for writing encrypted data.

Answer

s3:GetObject

Answer

s3:ListBucket

Answer

kms:GenerateDataKey

Question 3

A company is using Amazon SageMaker Ground Truth to create a labeled dataset for object detection. The labeling job is taking longer than expected. The team notices that many workers are spending a lot of time on images with no objects. Which labeling strategy should they use to reduce costs and time?

Accepted Answer

Create a pre-labeling task where workers only identify if an object exists, then send only positive images for full labeling.. Ground Truth supports automated data labeling and can use a pre-built model to filter out images with no objects. However, the most effective way is to use a pre-labeling task with a machine learning model to automatically reject images without objects. Alternatively, using a 'verify' labeling task where workers only verify if objects exist can be efficient. The best option is to use a 'verify' task mode, which is available for object detection.

Answer

Use a private workforce instead of public.

Answer

Use automated data labeling with a pre-trained model to filter empty images.

Answer

Increase the number of workers per dataset object.

Question 4

A data scientist needs to run a one-time training job on a large dataset using SageMaker. The job requires a specific PyTorch version and custom dependencies. Which approach is MOST efficient?

Accepted Answer

Use the SageMaker PyTorch estimator with a pre-built container.. SageMaker provides pre-built deep learning containers (DLCs) for PyTorch. Using a SageMaker framework estimator with a pre-built PyTorch container is the easiest and most efficient. The framework estimator automatically handles the container and dependencies. Creating a custom container is more work. Using the generic container requires manually installing dependencies. Using a notebook instance is for interactive development, not one-time training.

Answer

Create a custom Docker container and push to ECR.

Answer

Launch a SageMaker notebook instance, install dependencies, and run training script.

Answer

Use the SageMaker generic container and install PyTorch via a lifecycle configuration.

Question 5

Which TWO factors should be considered when choosing between Amazon SageMaker's real-time endpoints and serverless inference? (Select TWO.)

Accepted Answer

GPU requirement. Serverless inference is ideal for intermittent workloads with no cold start tolerance. Real-time endpoints are better for predictable, low-latency, and high-throughput requirements. GPU support is only available on real-time endpoints. Memory limits apply to both but serverless has a maximum of 6 GB. Concurrent requests can be handled by both, but serverless scales to zero.

Answer

Integration with AWS Lambda

Answer

Availability of built-in algorithms

Answer

Model size in GB

Question 6

Which THREE measures can help reduce inference latency for a deep learning model deployed on SageMaker real-time endpoints? (Select THREE.)

Accepted Answer

Enable SageMaker Neo to compile the model.. To reduce latency, use GPU instances, enable model compilation with SageMaker Neo, reduce input size, and use multi-model endpoints to share resources. However, multi-model endpoints add latency when switching models. Increasing batch size usually increases latency per request but can improve throughput. The three correct measures are: use GPU instances, enable SageMaker Neo, and reduce input data size.

Answer

Increase the batch size for inference.

Answer

Use a multi-model endpoint to share the instance.

Question 7

Which TWO actions are best practices for securing a SageMaker notebook instance? (Select TWO.)

Accepted Answer

Disable direct internet access for the notebook instance.. Best practices include using VPC to isolate the notebook, enabling encryption at rest, using IAM roles with least privilege, and disabling direct internet access. Direct internet access should be disabled to prevent data exfiltration. Root access should be disabled for notebook instances.

Answer

Enable root access for users to install packages.

Answer

Store data in the notebook's local storage for performance.

Answer

Use a shared IAM user for all data scientists.

Question 8

A data scientist is training a neural network on a GPU instance in Amazon SageMaker. The training job fails with an 'OutOfMemoryError'. Which action should the data scientist take to resolve this issue?

Accepted Answer

Reduce the batch size in the training script.. Option C is correct because reducing the batch size reduces memory usage per iteration. Option A is wrong because using a smaller instance type would have less memory. Option B is wrong because hyperparameter tuning does not directly reduce memory. Option D is wrong because distributed training typically increases memory usage per node.

Answer

Enable automatic hyperparameter tuning.

Answer

Switch to distributed training across multiple instances.

Answer

Use a smaller instance type with less GPU memory.

Question 9

A company is deploying a real-time inference endpoint using Amazon SageMaker. The model is a large deep learning model that requires low latency. The team is concerned about cost. Which SageMaker hosting option should the team use?

Accepted Answer

Use a SageMaker multi-model endpoint.. Option C is correct because multi-model endpoints share resources and reduce cost. Option A is wrong because it's for testing. Option B is wrong because serverless can have cold starts. Option D is wrong because batch transform is not real-time.

Answer

Use a SageMaker batch transform job.

Answer

Use a SageMaker Serverless Inference endpoint.

Answer

Use a single-instance endpoint with a large instance type.

Question 10

A machine learning engineer is deploying a model to an Amazon SageMaker endpoint. The model is a PyTorch model that requires a custom inference script. The engineer notices that the endpoint is returning 500 errors after deployment. Which step should the engineer take to debug the issue?

Accepted Answer

View the CloudWatch Logs for the endpoint.. Option D is correct because CloudWatch Logs contain detailed error messages. Option A is wrong because the endpoint is already deployed. Option B is wrong because it would overwrite the script. Option C is wrong because CloudWatch metrics show metrics, not errors.

Answer

Redeploy the endpoint with a different instance type.

Answer

Check the CloudWatch metrics for the endpoint.

Answer

Modify the inference script and update the endpoint.

Question 11

A data scientist is using AWS Glue to prepare training data. The job reads from an S3 bucket, performs transformations, and writes to another S3 bucket. The job is failing due to insufficient memory. Which solution should the data scientist use to fix this?

Accepted Answer

Increase the number of DPU (Data Processing Units) for the job.. Option C is correct because increasing the number of workers adds more memory. Option A is wrong because changing the file format does not increase memory. Option B is wrong because it's for ETL performance. Option D is wrong because using Athena is not a job.

Answer

Use AWS Glue's job bookmark feature.

Answer

Use Amazon Athena instead of AWS Glue.

Answer

Use a columnar file format like Parquet.

Question 12

A company is building a fraud detection model. The dataset is highly imbalanced (99% legitimate, 1% fraud). The data scientist trains a model using Amazon SageMaker's built-in XGBoost algorithm. The model achieves 99% accuracy but only catches 10% of fraud cases. Which technique should the data scientist apply to improve recall for the minority class?

Accepted Answer

Set the scale_pos_weight hyperparameter in XGBoost.. Option B is correct because setting scale_pos_weight balances class weights. Option A is wrong because SMOTE creates synthetic samples, but XGBoost has built-in handling. Option C is wrong because under-sampling loses data. Option D is wrong because it's for regression.

Answer

Use random under-sampling of the majority class.

Answer

Use mean squared error as the objective function.

Answer

Use SMOTE to oversample the minority class.

Question 13

A company uses Amazon SageMaker to train a model. The training job uses a custom Docker container. The job fails with the error 'CannotStartContainerError: API error (500).' Which of the following is the most likely cause?

Accepted Answer

The Docker image is built for a different CPU architecture.. Option D is correct because incompatible CPU instruction sets can cause container start failures. Option A is wrong because it would cause a different error. Option B is wrong because the error is during start. Option C is wrong because the error mentions container, not file system.

Answer

The training script has a syntax error.

Answer

The S3 input data is missing.

Answer

The output path is not writable.

Question 14

A data scientist needs to version control datasets used for machine learning experiments. Which AWS service should the data scientist use?

Accepted Answer

Amazon S3 with versioning enabled. Option C is correct because AWS Lake Formation does not version datasets. Option D is correct because Amazon S3 can be used with versioning enabled. Option A is wrong because it's for feature stores. Option B is wrong because it's for model registry.

Answer

AWS Lake Formation

Answer

Amazon SageMaker Feature Store

Answer

Amazon SageMaker Model Registry

Question 15

A company is using Amazon SageMaker to train a model on a large dataset stored in S3. The training job is taking a long time due to slow data loading. Which action can the data scientist take to reduce data loading time?

Accepted Answer

Use Pipe mode to stream data from S3.. Option D is correct because Pipe mode streams data directly. Option A is wrong because it doesn't change data transfer. Option B is wrong because it may be slower. Option C is wrong because it doesn't help.

Answer

Use File mode and copy data to Amazon EBS.

Answer

Use a larger instance type with more memory.

Answer

Enable data augmentation during training.