Palo Alto Networks

Free AWS Certified Machine Learning Engineer - Associate MLA-C01 Exam Braindumps
AWS Certified Machine Learning Engineer - Associate MLA-C01 Questions 89–96 (page: 13)

Updated On: 15-Apr-2026

Viewing Page 13 of 33 pages.

Download PDF version with 270 Questions

QUESTION: 89

An ML engineer needs to encrypt all data in transit when an ML training job runs. The ML engineer must ensure that encryption in transit is applied to processes that Amazon SageMaker uses during the training job.

Which solution will meet these requirements?

Encrypt communication between nodes for batch processing.
Encrypt communication between nodes in a training cluster.
Specify an AWS Key Management Service (AWS KMS) key during creation of the training job request.
Specify an AWS Key Management Service (AWS KMS) key during creation of the SageMaker domain.

Answer(s): B

Explanation:

Amazon SageMaker provides encryption in transit for training jobs by encrypting communication between nodes in a training cluster. This ensures that data remains secure when transferred between different compute instances within the cluster.
Encryption in transit is automatically enabled for distributed training jobs in SageMaker, which secures communication using TLS (Transport Layer Security). This helps protect sensitive data from interception or tampering during training.

Show Answer Next Question

QUESTION: 90

An ML engineer needs to use metrics to assess the quality of a time-series forecasting model.

Which metrics apply to this model? (Choose two.)

Recall
LogLoss
Root mean square error (RMSE)
InferenceLatency
Average weighted quantile loss (wQL)

Answer(s): C,E

Explanation:

For time-series forecasting models, the appropriate evaluation metrics focus on measuring the difference between predicted and actual values over time.
Root Mean Square Error (RMSE): RMSE measures the standard deviation of the residuals (prediction errors).
It is widely used in forecasting to quantify how well the model's predictions align with actual observations.
Average Weighted Quantile Loss (wQL): This metric is particularly useful in probabilistic forecasting. It evaluates how well the model predicts different quantiles of the forecast distribution, which is important for capturing uncertainty in time-series predictions.

Show Answer Next Question

QUESTION: 91

A company runs Amazon SageMaker ML models that use accelerated instances. The models require real-time responses. Each model has different scaling requirements. The company must not allow a cold start for the models.

Which solution will meet these requirements?

Create a SageMaker Serverless Inference endpoint for each model. Use provisioned concurrency for the endpoints.
Create a SageMaker Asynchronous Inference endpoint for each model. Create an auto scaling policy for each endpoint.
Create a SageMaker endpoint. Create an inference component for each model. In the inference component settings, specify the newly created endpoint. Create an auto scaling policy for each inference component.
Set the parameter for the minimum number of copies to at least 1.
Create an Amazon S3 bucket. Store all the model artifacts in the S3 bucket. Create a SageMaker multi- model endpoint. Point the endpoint to the S3 bucket. Create an auto scaling policy for the endpoint. Set the parameter for the minimum number of copies to at least 1.

Answer(s): C

Explanation:

Since the models require real-time responses and must avoid cold starts, SageMaker real-time inference endpoints are the best solution. Cold starts occur when there is no provisioned infrastructure to handle incoming requests, which is why setting the minimum number of instances to at least 1 ensures that a model is always ready to serve requests.
SageMaker real-time inference endpoints allow for scaling based on demand, ensuring optimal

performance.
Inference components allow each model to be managed independently within the same endpoint.

Auto scaling policies ensure that resources dynamically adjust based on the traffic, maintaining efficiency

while preventing unnecessary costs.
Setting a minimum number of copies to at least 1 prevents cold starts, ensuring real-time responsiveness.

Show Answer Next Question

QUESTION: 92

A company uses Amazon SageMaker for its ML process. A compliance audit discovers that an Amazon S3 bucket for training data uses server-side encryption with S3 managed keys (SSE-S3).

The company requires customer managed keys. An ML engineer changes the S3 bucket to use server-side encryption with AWS KMS keys (SSE-KMS). The ML engineer makes no other configuration changes.

After the change to the encryption settings, SageMaker training jobs start to fail with AccessDenied errors.

What should the ML engineer do to resolve this problem?

Update the IAM policy that is attached to the execution role for the training jobs. Include the s3:ListBucket and s3:GetObject permissions.
Update the S3 bucket policy that is attached to the S3 bucket. Set the value of the aws:SecureTransport condition key to True.
Update the IAM policy that is attached to the execution role for the training jobs. Include the kms:Encrypt and kms:Decrypt permissions.
Update the IAM policy that is attached to the user that created the training jobs. Include the kms:CreateGrant permission.

Answer(s): C

Explanation:

When changing the S3 bucket encryption from SSE-S3 (Amazon S3 managed keys) to SSE-KMS (AWS KMS keys), additional permissions are required for AWS services, such as SageMaker, to access the encrypted data. The AccessDenied error occurs because the SageMaker execution role lacks the necessary AWS Key Management Service (KMS) permissions to decrypt the training data.
To fix this issue, the IAM execution role used by SageMaker for training must have the following permissions for the KMS key:
kms:Decrypt To read encrypted data from S3.

kms:Encrypt To store encrypted output (if required).

kms:GenerateDataKey To allow SageMaker to obtain the encryption key.

Updating the execution role with these permissions ensures that SageMaker can successfully access the training data stored in the S3 bucket with SSE-KMS encryption.

Show Answer Next Question

QUESTION: 93

A company runs training jobs on Amazon SageMaker by using a compute optimized instance. Demand for training runs will remain constant for the next 55 weeks. The instance needs to run for 35 hours each week.
The company needs to reduce its model training costs.

Which solution will meet these requirements?

Use a serverless endpoint with a provisioned concurrency of 35 hours for each week. Run the training on the endpoint.
Use SageMaker Edge Manager for the training. Specify the instance requirement in the edge device configuration. Run the training.
Use the heterogeneous cluster feature of SageMaker Training. Configure the instance_type, instance_count, and instance_groups arguments to run training jobs.
Opt in to a SageMaker Savings Plan with a 1-year term and an All Upfront payment. Run a SageMaker Training job on the instance.

Answer(s): D

Explanation:

Since the demand for training jobs remains constant for the next 55 weeks, and the company requires 35 hours per week, the best cost-saving option is to use a SageMaker Savings Plan with a 1-year term and All Upfront payment.
SageMaker Savings Plans provide significant cost reductions (up to 64%) compared to On-Demand pricing.

A 1-year term aligns well with the expected duration of training needs (55 weeks).

All Upfront payment offers the highest discount, reducing long-term costs.

Unlike Reserved Instances, SageMaker Savings Plans provide flexibility to use different instance types as long as the commitment is met.

Show Answer Next Question

QUESTION: 94

HOTSPOT

A company needs to train an ML model that will use historical transaction data to predict customer behavior.

Select the correct AWS service from the following list to perform each task on the data. Each service should be selected one time or not at all.

Amazon Athena AWS Glue
Amazon Kinesis Data Streams
Amazon S3

Hot Area:

See Explanation section for answer.

Answer(s): A

Explanation:

Query the data: Amazon Athena
Amazon Athena is an interactive query service that allows you to analyze structured data stored in Amazon S3 using SQL. It is ideal for querying historical transaction data.

Store the data: Amazon S3
Amazon S3 is a scalable and durable storage service used to store large amounts of historical transaction data, making it the best choice for data storage in this scenario.

Transform the data: AWS Glue
AWS Glue is a fully managed extract, transform, and load (ETL) service that helps clean, normalize, and prepare data for ML model training.

Show Answer Next Question

QUESTION: 95

A company deployed an ML model that uses the XGBoost algorithm to predict product failures. The model is hosted on an Amazon SageMaker endpoint and is trained on normal operating data. An AWS Lambda function provides the predictions to the company's application.

An ML engineer must implement a solution that uses incoming live data to detect decreased model accuracy over time.

Which solution will meet these requirements?

Use Amazon CloudWatch to create a dashboard that monitors real-time inference data and model predictions. Use the dashboard to detect drift.
Modify the Lambda function to calculate model drift by using real-time inference data and model predictions. Program the Lambda function to send alerts.
Schedule a monitoring job in SageMaker Model Monitor. Use the job to detect drift by analyzing the live data against a baseline of the training data statistics and constraints.
Schedule a monitoring job in SageMaker Debugger. Use the job to detect drift by analyzing the live data against a baseline of the training data statistics and constraints.

Answer(s): C

Explanation:

SageMaker Model Monitor is designed to continuously track model quality and detect data drift by comparing incoming live data against a baseline dataset derived from training data. It can automatically identify changes in data distributions, which helps in detecting decreased model accuracy over time.
It works by profiling data statistics (such as feature distributions) and setting constraints based on the

training data.
When live inference data deviates significantly from the baseline, SageMaker Model Monitor generates

alerts so corrective actions can be taken.

Show Answer Next Question

QUESTION: 96

A company has an ML model that uses historical transaction data to predict customer behavior. An ML engineer is optimizing the model in Amazon SageMaker to enhance the model's predictive accuracy. The ML engineer must examine the input data and the resulting predictions to identify trends that could skew the model's performance across different demographics.

Which solution will provide this level of analysis?

Use Amazon CloudWatch to monitor network metrics and CPU metrics for resource optimization during model training.
Create AWS Glue DataBrew recipes to correct the data based on statistics from the model output.
Use SageMaker Clarify to evaluate the model and training data for underlying patterns that might affect accuracy.
Create AWS Lambda functions to automate data pre-processing and to ensure consistent quality of input data for the model.

Answer(s): C

Explanation:

Amazon SageMaker Clarify is specifically designed to detect bias in data and models and provides explainability for ML models. It helps identify trends or disparities in predictions across different demographics, ensuring the model is not skewed toward specific groups.
It evaluates training data for imbalances or biases.

It provides insights into feature importance, helping understand how different factors contribute to

predictions.
It helps detect disparities in model predictions across different segments of data.

Show Answer Next Question

10
11
12
13
14
15
…
20
30

Download PDF Next Page

Viewing page 13 of 33
Viewing questions 97 - 104 out of 270 questions

Post your Comments and Discuss Amazon AWS Certified Machine Learning Engineer - Associate MLA-C01 exam prep with other Community members:

Comments:

Name:

AI Tutor

AI Tutor 👋 I’m here to help!