MLS-C01 practice questions 31–40

1. Question 31 · 368 in bank

   A machine learning specialist is developing a proof of concept for government users whose primary concern is security. The specialist is using Amazon SageMaker to train a convolutional neural network (CNN) model for a photo classifier application. The specialist wants to protect the data so that it cannot be accessed and transferred to a remote host by malicious code accidentally installed on the training container. Which action will provide the MOST secure protection?

   • ARemove Amazon S3 access permissions from the SageMaker execution role.
   • BEncrypt the weights of the CNN model.
   • CEncrypt the training and validation dataset.
   • DEnable network isolation for training jobs.

   Show answer

   Answer: D

   Explanation

   I will go with D, "cannot be accessed and transferred to a remote host by malicious code accidentally installed on the training container" Based on the following link: https://aws.amazon.com/blogs/security/secure-deployment-of-amazon-sagemaker-resources/ "EnableNetworkIsolation – Set this to true when creating training, hyperparameter tuning, and inference jobs to prevent situations like malicious code being accidentally installed and transferring data to a remote host."

   Source: Adapted from community discussion — AShahine21

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

2. Question 32 · 368 in bank

   A medical imaging company wants to train a computer vision model to detect areas of concern on patients' CT scans. The company has a large collection of unlabeled CT scans that are linked to each patient and stored in an Amazon S3 bucket. The scans must be accessible to authorized users only. A machine learning engineer needs to build a labeling pipeline. Which set of steps should the engineer take to build the labeling pipeline with the LEAST effort?

   • ACreate a workforce with AWS Identity and Access Management (IAM). Build a labeling tool on Amazon EC2 Queue images for labeling by using Amazon Simple Queue Service (Amazon SQS). Write the labeling instructions.
   • BCreate an Amazon Mechanical Turk workforce and manifest file. Create a labeling job by using the built-in image classification task type in Amazon SageMaker Ground Truth. Write the labeling instructions.
   • CCreate a private workforce and manifest file. Create a labeling job by using the built-in bounding box task type in Amazon SageMaker Ground Truth. Write the labeling instructions.
   • DCreate a workforce with Amazon Cognito. Build a labeling web application with AWS Amplify. Build a labeling workflow backend using AWS Lambda. Write the labeling instructions.

   Show answer

   Answer: C

   Explanation

   I would answer C, because of the requirement that authorized users should only have access. These users will comprise the private workforce of AWS Ground Truth. See documentation: https://docs.aws.amazon.com/sagemaker/latest/dg/sms-workforce-private.html

   Source: Adapted from community discussion — [Removed]

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

3. Question 33 · 368 in bank

   A company is using Amazon Textract to extract textual data from thousands of scanned text-heavy legal documents daily. The company uses this information to process loan applications automatically. Some of the documents fail business validation and are returned to human reviewers, who investigate the errors. This activity increases the time to process the loan applications. What should the company do to reduce the processing time of loan applications?

   • AConfigure Amazon Textract to route low-confidence predictions to Amazon SageMaker Ground Truth. Perform a manual review on those words before performing a business validation.
   • BUse an Amazon Textract synchronous operation instead of an asynchronous operation.
   • CConfigure Amazon Textract to route low-confidence predictions to Amazon Augmented AI (Amazon A2I). Perform a manual review on those words before performing a business validation.
   • DUse Amazon Rekognition's feature to detect text in an image to extract the data from scanned images. Use this information to process the loan applications.

   Show answer

   Answer: C

   Explanation

   the differences rely on the function of these two service. Ground Truth is used for "labeling" typically, text or image label: if the service cannot automatically label the data, it send to ground truth and wait for human to label it. but A2I is for validate prediction. The model already predict the results and human then add views to it.

   Source: Adapted from community discussion — ZSun

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

4. Question 34 · 368 in bank

   A company ingests machine learning (ML) data from web advertising clicks into an Amazon S3 data lake. Click data is added to an Amazon Kinesis data stream by using the Kinesis Producer Library (KPL). The data is loaded into the S3 data lake from the data stream by using an Amazon Kinesis Data Firehose delivery stream. As the data volume increases, an ML specialist notices that the rate of data ingested into Amazon S3 is relatively constant. There also is an increasing backlog of data for Kinesis Data Streams and Kinesis Data Firehose to ingest. Which next step is MOST likely to improve the data ingestion rate into Amazon S3?

   • AIncrease the number of S3 prefixes for the delivery stream to write to.
   • BDecrease the retention period for the data stream.
   • CIncrease the number of shards for the data stream.
   • DAdd more consumers using the Kinesis Client Library (KCL).

   Show answer

   Answer: C

   Explanation

   C is the correct answer. # of shard is determined by: 1. # of transactions per second times 2. data blob eg. 100 KB in size 3. One shard can Ingest 1 MB/second

   Source: Adapted from community discussion — SophieSu

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

5. Question 35 · 368 in bank

   The displayed graph is from a forecasting model for testing a time series.

   

   Considering the graph only, which conclusion should a Machine Learning Specialist make about the behavior of the model?

   • AThe model predicts both the trend and the seasonality well
   • BThe model predicts the trend well, but not the seasonality.
   • CThe model predicts the seasonality well, but not the trend.
   • DThe model does not predict the trend or the seasonality well.

   Show answer

   Answer: A

   Explanation

   agreed, this seems to be A. there is similarity between the blue and green lines as far as capturing trend and seasonality is concerned. It just seems that if assumption is that the model is a linear regression model then just the intercept is off by a few units.

   Source: Adapted from community discussion — VR10

   Next question

6. Question 36 · 368 in bank

   A data scientist must build a custom recommendation model in Amazon SageMaker for an online retail company. Due to the nature of the company's products, customers buy only 4-5 products every 5-10 years. So, the company relies on a steady stream of new customers. When a new customer signs up, the company collects data on the customer's preferences. Below is a sample of the data available to the data scientist.

   

   How should the data scientist split the dataset into a training and test set for this use case?

   • AShuffle all interaction data. Split off the last 10% of the interaction data for the test set.
   • BIdentify the most recent 10% of interactions for each user. Split off these interactions for the test set.
   • CIdentify the 10% of users with the least interaction data. Split off all interaction data from these users for the test set.
   • DRandomly select 10% of the users. Split off all interaction data from these users for the test set.

   Show answer

   Answer: B

   Explanation

   I think the answer is D because customers by only 4-5 products every 5-10 years so it doesn't make sense to get 10% interactions for each user as a test set.

   Source: Adapted from community discussion — NicZ1111

   References

   • AWS documentation

   Next question

7. Question 37 · 368 in bank

   Select 3

   A financial services company wants to adopt Amazon SageMaker as its default data science environment. The company's data scientists run machine learning (ML) models on confidential financial data. The company is worried about data egress and wants an ML engineer to secure the environment. Which mechanisms can the ML engineer use to control data egress from SageMaker? (Choose three.)

   • AConnect to SageMaker by using a VPC interface endpoint powered by AWS PrivateLink.
   • BUse SCPs to restrict access to SageMaker.
   • CDisable root access on the SageMaker notebook instances.
   • DEnable network isolation for training jobs and models.
   • ERestrict notebook presigned URLs to specific IPs used by the company.
   • FProtect data with encryption at rest and in transit. Use AWS Key Management Service (AWS KMS) to manage encryption keys.

   Show answer

   Answer: ADE

   Explanation

   ADF - the concepts in ADF are explained in detail on the official Amazon Exam Readiness Exam Readiness: AWS Certified Machine Learning - Specialty. Amazon official materials do not mention other concepts in BCE.

   Source: Adapted from community discussion — SophieSu

   References

   • AWS documentation
   • AWS documentation

   Next question

8. Question 38 · 368 in bank

   A company is converting a large number of unstructured paper receipts into images. The company wants to create a model based on natural language processing (NLP) to find relevant entities such as date, location, and notes, as well as some custom entities such as receipt numbers. The company is using optical character recognition (OCR) to extract text for data labeling. However, documents are in different structures and formats, and the company is facing challenges with setting up the manual workflows for each document type. Additionally, the company trained a named entity recognition (NER) model for custom entity detection using a small sample size. This model has a very low confidence score and will require retraining with a large dataset. Which solution for text extraction and entity detection will require the LEAST amount of effort?

   • AExtract text from receipt images by using Amazon Textract. Use the Amazon SageMaker BlazingText algorithm to train on the text for entities and custom entities.
   • BExtract text from receipt images by using a deep learning OCR model from the AWS Marketplace. Use the NER deep learning model to extract entities.
   • CExtract text from receipt images by using Amazon Textract. Use Amazon Comprehend for entity detection, and use Amazon Comprehend custom entity recognition for custom entity detection.
   • DExtract text from receipt images by using a deep learning OCR model from the AWS Marketplace. Use Amazon Comprehend for entity detection, and use Amazon Comprehend custom entity recognition for custom entity detection.

   Show answer

   Answer: C

   Explanation

   C is the correct answer. You definitely need Amazon Textract service which eliminate options B & D. Between A & C - Comprehend will quicker.

   Source: Adapted from community discussion — exam_prep

   References

   • AWS documentation

   Next question

9. Question 39 · 368 in bank

   A company is building a predictive maintenance model based on machine learning (ML). The data is stored in a fully private Amazon S3 bucket that is encrypted at rest with AWS Key Management Service (AWS KMS) CMKs. An ML specialist must run data preprocessing by using an Amazon SageMaker Processing job that is triggered from code in an Amazon SageMaker notebook. The job should read data from Amazon S3, process it, and upload it back to the same S3 bucket. The preprocessing code is stored in a container image in Amazon Elastic Container Registry (Amazon ECR). The ML specialist needs to grant permissions to ensure a smooth data preprocessing workflow. Which set of actions should the ML specialist take to meet these requirements?

   • ACreate an IAM role that has permissions to create Amazon SageMaker Processing jobs, S3 read and write access to the relevant S3 bucket, and appropriate KMS and ECR permissions. Attach the role to the SageMaker notebook instance. Create an Amazon SageMaker Processing job from the notebook.
   • BCreate an IAM role that has permissions to create Amazon SageMaker Processing jobs. Attach the role to the SageMaker notebook instance. Create an Amazon SageMaker Processing job with an IAM role that has read and write permissions to the relevant S3 bucket, and appropriate KMS and ECR permissions.
   • CCreate an IAM role that has permissions to create Amazon SageMaker Processing jobs and to access Amazon ECR. Attach the role to the SageMaker notebook instance. Set up both an S3 endpoint and a KMS endpoint in the default VPC. Create Amazon SageMaker Processing jobs from the notebook.
   • DCreate an IAM role that has permissions to create Amazon SageMaker Processing jobs. Attach the role to the SageMaker notebook instance. Set up an S3 endpoint in the default VPC. Create Amazon SageMaker Processing jobs with the access key and secret key of the IAM user with appropriate KMS and ECR permissions.

   Show answer

   Answer: B

   Explanation

   Confusing between A and B. Leaning to B The main difference between A and B is the IAM role that is attached to the SageMaker notebook instance. In A, the role has permissions to access the data, the container image, and the KMS CMK. In B, the role only has permissions to create SageMaker Processing jobs. This means that in A, the notebook instance can potentially access or modify the data or the image without using a Processing job, which is not desirable. In B, the notebook instance can only create Processing jobs, and the Processing jobs themselves have a separate IAM role that grants them access to the data, the image, and the KMS CMK. This way, the data and the image are only accessed by the Processing jobs, which are more secure and controlled than the notebook instance.

   Source: Adapted from community discussion — Mickey321

   References

   • AWS documentation
   • AWS documentation

   Next question

10. Question 40 · 368 in bank

    A data scientist has been running an Amazon SageMaker notebook instance for a few weeks. During this time, a new version of Jupyter Notebook was released along with additional software updates. The security team mandates that all running SageMaker notebook instances use the latest security and software updates provided by SageMaker. How can the data scientist meet this requirements?

    • ACall the CreateNotebookInstanceLifecycleConfig API operation
    • BCreate a new SageMaker notebook instance and mount the Amazon Elastic Block Store (Amazon EBS) volume from the original instance
    • CStop and then restart the SageMaker notebook instance
    • DCall the UpdateNotebookInstanceLifecycleConfig API operation

    Show answer

    Answer: C

    References

    • AWS documentation

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

MLS-C01 practice, question 31. 368 questions available.