MLS-C01 Machine Learning Implementation and Operations Practice Test 17 — 15 Questions

Question 1

A company uses Amazon SageMaker to train a model. The training job fails with an 'OutOfMemory' error. The training data is stored in S3 and the instance type is ml.m5.xlarge. What is the most efficient way to resolve this issue?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Use a larger instance type, such as ml.m5.2xlarge. The 'OutOfMemory' error indicates that the ml.m5.xlarge instance (4 vCPUs, 16 GiB memory) does not have enough RAM to hold the training data and model during processing. Upgrading to ml.m5.2xlarge (8 vCPUs, 32 GiB memory) directly increases available memory, resolving the issue without requiring code changes or architectural modifications. This is the most efficient solution because it requires no script alterations and leverages SageMaker's built-in instance scaling.

Answer

Enable managed spot training

Answer

Reduce the batch size in the training script

Answer

Increase the number of instances using distributed training

Question 2

A team uses AWS Glue ETL jobs to preprocess data for SageMaker training. The job runs successfully but the output data is empty. What is the most likely cause?

Accepted Answer

The filter transformation condition is too restrictive, removing all rows. A filter transformation in AWS Glue ETL jobs can remove all rows if the condition is too restrictive, resulting in an empty output dataset. This is a common logic error where the filter predicate (e.g., `df.filter("value > 100")`) matches no records, causing the DynamicFrame to be empty after transformation. The job succeeds because no runtime error occurs, but the output is empty.

Answer

There is a data type mismatch between source and target

Answer

The source data is partitioned and only a subset of partitions is read

Answer

The Glue job runs out of memory and fails silently

Question 3

A company uses SageMaker to host a model for real-time predictions. The model is updated weekly. To minimize downtime during model updates, what should the company do?

Accepted Answer

Create a new endpoint configuration with the new model and update the endpoint to use the new configuration. SageMaker allows you to create a new endpoint configuration with the updated model and then update the existing endpoint to use this new configuration. This triggers a rolling update where SageMaker gradually shifts traffic from the old model to the new one, ensuring zero downtime during the transition. The endpoint remains available throughout the process, and you can roll back quickly if needed by reverting to the previous configuration.

Answer

Create a second endpoint with the new model and use an Application Load Balancer to route traffic

Answer

Update the existing endpoint configuration with the new model URL

Answer

Delete the existing endpoint and create a new one with the updated model

Question 4

A company is using SageMaker to host a model that makes predictions on streaming data from Amazon Kinesis. The model must provide predictions with sub-second latency. Which approach should the company use?

Accepted Answer

Use a SageMaker real-time endpoint and invoke it from an AWS Lambda function that is triggered by Kinesis. A SageMaker real-time endpoint provides sub-second latency for individual predictions, and invoking it from an AWS Lambda function triggered by Kinesis allows each streaming record to be processed synchronously with low overhead. This architecture meets the requirement for low-latency predictions on streaming data.

Answer

Use SageMaker asynchronous inference with a Kinesis trigger

Answer

Use Amazon Kinesis Data Analytics with a built-in ML model

Answer

Use SageMaker batch transform to process batches of records from Kinesis

Question 5

A team is using SageMaker to train a model. They want to track hyperparameters, metrics, and model artifacts. Which SageMaker feature should they use?

Accepted Answer

SageMaker Experiments. SageMaker Experiments is the correct choice because it is purpose-built for tracking hyperparameters, metrics, and model artifacts across training runs. It automatically captures input parameters, output metrics, and artifact locations (e.g., S3 paths) for each trial, enabling comparison and lineage tracking without manual logging.

Answer

SageMaker Pipelines

Answer

SageMaker Debugger

Answer

SageMaker Model Registry

Question 6

A company is deploying a SageMaker model for real-time inference. The endpoint must be highly available and cost-effective. Which TWO actions should the company take? (Select TWO.)

Accepted Answer

Deploy the endpoint with at least two instances in different Availability Zones. Deploying a SageMaker endpoint with at least two instances in different Availability Zones (AZs) ensures high availability by eliminating a single point of failure. If one AZ goes down, traffic is automatically routed to the healthy instance in the other AZ, meeting the requirement for a highly available real-time inference endpoint.

Answer

Use managed spot training for inference

Answer

Use GPU instances for all models even if not required

Answer

Use a single large instance to handle peak load

Question 7

A company uses SageMaker to train a model. The training job is taking too long and the data scientist wants to speed it up. Which THREE strategies should the data scientist consider? (Select THREE.)

Accepted Answer

Use a GPU instance type like ml.p3.2xlarge. Option B is correct because switching to a GPU instance type such as ml.p3.2xlarge provides hardware acceleration (NVIDIA V100 GPUs) that dramatically speeds up the matrix/tensor computations used in deep learning training compared to CPU-only instances. Option C is correct because distributed training spreads the workload across multiple instances (using SageMaker's distributed data parallel or model parallel libraries), reducing the wall-clock time of a training job by parallelizing gradient computation and updates. Option D is correct because Pipe input mode streams data directly from Amazon S3 to the training container instead of downloading the full dataset first, eliminating the initial download bottleneck and improving throughput for large datasets. Option A is not appropriate because reducing epochs changes the model's training convergence and can degrade accuracy rather than being a legitimate speed optimization. Option E is not appropriate because increasing batch size alone does not guarantee faster training and can affect convergence, memory usage, and model quality without addressing the underlying compute or I/O bottleneck.

Answer

Reduce the number of training epochs

Answer

Increase the batch size in the training script

Question 8

A SageMaker endpoint has a CloudWatch alarm configured as shown in the exhibit. The alarm fires when the p99 latency exceeds 500 ms for two consecutive minutes. Which action should the data scientist take to reduce latency?

Accepted Answer

Increase the number of instances behind the endpoint. Increasing the number of instances behind the endpoint adds more compute capacity to handle the inference requests, which directly reduces the queuing and processing time for each request. Since the alarm triggers when p99 latency exceeds 500 ms for two consecutive minutes, scaling out horizontally distributes the load and lowers tail latency.

Answer

Increase the batch size in the inference request

Answer

Use SageMaker asynchronous inference instead of real-time

Answer

Switch to GPU instances even if the model does not require GPU

Question 9

A company is using Amazon SageMaker Ground Truth to create labeled datasets for a text classification task. The labeling job uses a private workforce of 10 annotators. After labeling 10,000 items, the quality of labels is inconsistent. Which approach will MOST effectively improve labeling consistency?

Accepted Answer

Configure the labeling job to use annotation consolidation with majority voting and require multiple annotations per item.. Requiring multiple annotations per item and using annotation consolidation with majority voting directly improves labeling consistency by reducing individual annotator bias and ensuring that the final label is based on consensus. Option A is incorrect because removing annotations from low-agreement annotators after the job completes does not improve the quality of labels already assigned; it may also discard valid data. Option B is incorrect because simply increasing the number of annotators does not guarantee consistency; it may introduce more variance without a consolidation mechanism. Option D is incorrect because active learning is used to select which items to label, not to improve the consistency of labeling; it does not address the inconsistency in the labeling process itself.

Answer

Remove annotations from annotators with low agreement after the job completes.

Answer

Increase the number of annotators to 20 to average out inconsistencies.

Answer

Use active learning to automatically label the most confident samples and only send uncertain ones to annotators.

Question 10

A data scientist trains a model using Amazon SageMaker's built-in XGBoost algorithm. The model overfits on the training data. Which hyperparameter adjustment is MOST likely to reduce overfitting?

Accepted Answer

Increase the value of the lambda (L2 regularization) hyperparameter.. Increasing the lambda (L2 regularization) hyperparameter adds a penalty on the squared magnitude of the model weights, which discourages the model from fitting noise in the training data. This directly reduces overfitting by shrinking the influence of individual features, a standard regularization technique in XGBoost.

Answer

Increase the value of the max_depth hyperparameter.

Answer

Increase the value of the subsample hyperparameter to 1.0.

Answer

Increase the value of the num_round hyperparameter.

Question 11

A company is using Amazon SageMaker to train a deep learning model for image classification. The training job is using a single p3.2xlarge instance and takes 10 hours. The data scientist wants to reduce training time using distributed training. Which SageMaker feature should be used?

Accepted Answer

Use the SageMaker distributed data parallelism library with multiple p3.2xlarge instances.. The goal is to reduce training time, and the SageMaker distributed data parallelism library is designed to split the mini-batch across multiple GPU instances, enabling synchronous or asynchronous gradient updates that scale near-linearly with the number of instances. By adding more p3.2xlarge instances, the effective throughput increases, directly reducing wall-clock training time for the image classification model.

Answer

Use SageMaker Managed Spot Training to reduce cost, but training time remains the same.

Answer

Use SageMaker Hyperparameter Tuning to find optimal hyperparameters faster.

Answer

Use the SageMaker distributed model parallelism library with a single p3dn.24xlarge instance.

Question 12

A company is deploying a machine learning model using Amazon SageMaker. The model needs to be updated frequently with new data. Which TWO approaches can be used to update the model without downtime? (Choose TWO.)

Accepted Answer

Use SageMaker A/B testing to gradually shift traffic to the new model variant.. Option C is correct because SageMaker A/B testing (production variants on a single endpoint) lets you deploy a new model variant alongside the existing one and gradually shift traffic to it, so users continue to be served without downtime. Option E is correct because a blue/green deployment runs the new model on a separate endpoint and then switches traffic (e.g., via DNS/Route 53 weighted records or an endpoint update), allowing a safe cutover with no service interruption. Option A is wrong because deleting the existing endpoint removes the serving capacity and causes downtime before the new endpoint is available. Option B is wrong because you cannot directly modify a model artifact in a live endpoint configuration; SageMaker endpoints are immutable and require creating a new endpoint configuration and updating the endpoint. Option D is wrong because stopping the endpoint takes the model offline, producing downtime during the update and restart.

Answer

Delete the existing endpoint and create a new one with the updated model.

Answer

Directly update the model artifact in the existing endpoint configuration.

Answer

Stop the endpoint, update the model, and restart the endpoint.

Question 13

A company is building a machine learning pipeline on AWS. The pipeline includes data ingestion, preprocessing, training, and deployment. Which THREE AWS services can be used to orchestrate the pipeline? (Choose THREE.)

Accepted Answer

AWS Glue Workflows. AWS Glue Workflows (A) is correct because it is a purpose-built orchestration feature of AWS Glue that lets you define and trigger a directed acyclic graph (DAG) of crawlers and ETL jobs, making it suitable for orchestrating the data ingestion and preprocessing stages of an ML pipeline. Amazon SageMaker Pipelines (C) is correct because it is a native CI/CD orchestration service for ML that models each step (processing, training, evaluation, conditional/deployment) as a pipeline step with dependencies, directly covering the full ingestion-to-deployment lifecycle. AWS Step Functions (E) is correct because its state machine language can coordinate Lambda functions, SageMaker jobs, Glue jobs, and other services in sequence, parallel, or with branching/retries, providing general-purpose orchestration across the whole pipeline. Amazon CloudWatch (B) is a monitoring and observability service for metrics, logs, and alarms, not a workflow orchestrator, and AWS Lambda (D) is a compute service for running individual functions that can be invoked by an orchestrator but does not itself provide pipeline orchestration.

Answer

Amazon CloudWatch

Answer

AWS Lambda

Question 14

A data scientist wants to deploy a PyTorch model for real-time inference with low latency. Which AWS service should they use?

Accepted Answer

Amazon SageMaker real-time endpoint. Amazon SageMaker real-time endpoints are specifically designed for low-latency inference on deployed models, including PyTorch models. They provide persistent HTTPS endpoints that autoscale and support custom containers, making them ideal for real-time prediction workloads.

Answer

Amazon Elastic Container Service (ECS)

Answer

Amazon SageMaker batch transform

Answer

AWS Lambda

Question 15

A company's ML model training on Amazon SageMaker is taking longer than expected. The training job uses a single ml.p3.2xlarge instance. Which change is most likely to reduce training time?

Accepted Answer

Use distributed training with multiple GPU instances. The training job is bottlenecked by compute capacity, as a single ml.p3.2xlarge instance provides only one NVIDIA V100 GPU. Distributed training with multiple GPU instances (e.g., multiple ml.p3.2xlarge instances) enables data parallelism, splitting the workload across GPUs and significantly reducing wall-clock training time for large models or datasets.

Answer

Increase the instance's EBS volume size

Answer

Enable Managed Spot Training

Answer

Switch to a compute-optimized instance with more vCPUs