MLS-C01 practice questions 341–350

1. Question 341 · 368 in bank

   Select 2

   A Machine Learning team runs its own training algorithm on Amazon SageMaker. The training algorithm requires external assets. The team needs to submit both its own algorithm code and algorithm-specific parameters to Amazon SageMaker. What combination of services should the team use to build a custom algorithm in Amazon SageMaker? (Choose two.)

   • AAWS Secrets Manager
   • BAWS CodeStar
   • CAmazon ECR
   • DAmazon ECS
   • EAmazon S3

   Show answer

   Answer: CE

   Explanation

   CE based on criteria and this documentation: https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-mkt-create-model-package.html "For Location of inference image, type the path to the image that contains your inference code. The image must be stored as a Docker container in Amazon ECR. For Location of model data artifacts, type the location in S3 where your model artifacts are stored."

   Source: Adapted from community discussion — [Removed]

   References

   • AWS documentation
   • AWS documentation

   Next question

2. Question 342 · 368 in bank

   A Machine Learning Specialist wants to determine the appropriate SageMakerVariantInvocationsPerInstance setting for an endpoint automatic scaling configuration. The Specialist has performed a load test on a single instance and determined that peak requests per second (RPS) without service degradation is about 20 RPS. As this is the first deployment, the Specialist intends to set the invocation safety factor to 0.5. Based on the stated parameters and given that the invocations per instance setting is measured on a per-minute basis, what should the Specialist set as the SageMakerVariantInvocationsPerInstance setting?

   • A10
   • B30
   • C600
   • D2,400

   Show answer

   Answer: C

   References

   • AWS documentation

   Next question

3. Question 343 · 368 in bank

   A company uses a long short-term memory (LSTM) model to evaluate the risk factors of a particular energy sector. The model reviews multi-page text documents to analyze each sentence of the text and categorize it as either a potential risk or no risk. The model is not performing well, even though the Data Scientist has experimented with many different network structures and tuned the corresponding hyperparameters. Which approach will provide the MAXIMUM performance boost?

   • AInitialize the words by term frequency-inverse document frequency (TF-IDF) vectors pretrained on a large collection of news articles related to the energy sector.
   • BUse gated recurrent units (GRUs) instead of LSTM and run the training process until the validation loss stops decreasing.
   • CReduce the learning rate and run the training process until the training loss stops decreasing.
   • DInitialize the words by word2vec embeddings pretrained on a large collection of news articles related to the energy sector.

   Show answer

   Answer: D

   Explanation

   D is correct. C is not the best the answer because the question states that tuning parameters doesn't help a lot. Transfer learning would be better solution!

   Source: Adapted from community discussion — SophieSu

   Next question

4. Question 344 · 368 in bank

   Select 2

   A Machine Learning Specialist needs to move and transform data in preparation for training. Some of the data needs to be processed in near-real time, and other data can be moved hourly. There are existing Amazon EMR MapReduce jobs to clean and feature engineering to perform on the data. Which of the following services can feed data to the MapReduce jobs? (Choose two.)

   • AAWS DMS
   • BAmazon Kinesis
   • CAWS Data Pipeline
   • DAmazon Athena
   • EAmazon ES

   Show answer

   Answer: BC

   Explanation

   AWS Data Pipeline (Option C) can be used to move the hourly data, as it provides a way to move data from various sources to Amazon EMR for processing. Amazon Kinesis (Option B) can be used to process data in near-real time, as it is a real-time data streaming service that can handle large amounts of incoming data from multiple sources. The data can be fed to Amazon EMR MapReduce jobs for processing.

   Source: Adapted from community discussion — AjoseO

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

5. Question 345 · 368 in bank

   A Machine Learning Specialist previously trained a logistic regression model using scikit-learn on a local machine, and the Specialist now wants to deploy it to production for inference only. What steps should be taken to ensure Amazon SageMaker can host a model that was trained locally?

   • ABuild the Docker image with the inference code. Tag the Docker image with the registry hostname and upload it to Amazon ECR.
   • BSerialize the trained model so the format is compressed for deployment. Tag the Docker image with the registry hostname and upload it to Amazon S3.
   • CSerialize the trained model so the format is compressed for deployment. Build the image and upload it to Docker Hub.
   • DBuild the Docker image with the inference code. Configure Docker Hub and upload the image to Amazon ECR.

   Show answer

   Answer: A

   Explanation

   A. YES - the inference code is built after inspecting the coefficient of the Linear Model (or, alternatively, the model can be serialized via pickle and the inference code is simply to unserialized the mode); ECR is only registry supported by SageMaer; tagging the Docker image with the registry hostname (eg. docker tag image1 public.ecr.aws/g6h7x5m5/image1) is required so that the docker push command knows where to push the image B. NO - no need to compress; image must be on ECR C. NO - no need to compress; image must be on ECR D. NO - image must be on ECR

   Source: Adapted from community discussion — loict

   Next question

6. Question 346 · 368 in bank

   A trucking company is collecting live image data from its fleet of trucks across the globe. The data is growing rapidly and approximately 100 GB of new data is generated every day. The company wants to explore machine learning uses cases while ensuring the data is only accessible to specific IAM users. Which storage option provides the most processing flexibility and will allow access control with IAM?

   • AUse a database, such as Amazon DynamoDB, to store the images, and set the IAM policies to restrict access to only the desired IAM users.
   • BUse an Amazon S3-backed data lake to store the raw images, and set up the permissions using bucket policies.
   • CSetup up Amazon EMR with Hadoop Distributed File System (HDFS) to store the files, and restrict access to the EMR instances using IAM policies.
   • DConfigure Amazon EFS with IAM policies to make the data available to Amazon EC2 instances owned by the IAM users.

   Show answer

   Answer: B

   Explanation

   C is not affordable because it is ephemeral storage. https://docs.aws.amazon.com/emr/latest/ManagementGuide/emr-plan-file-systems.html "HDFS is used by the master and core nodes. One advantage is that it's fast; a disadvantage is that it's ephemeral storage which is reclaimed when the cluster ends. It's best used for caching the results produced by intermediate job-flow steps."

   Source: Adapted from community discussion — KlaudYu

   References

   • AWS documentation
   • AWS documentation

   Next question

7. Question 347 · 368 in bank

   A manufacturing company has structured and unstructured data stored in an Amazon S3 bucket. A Machine Learning Specialist wants to use SQL to run queries on this data. Which solution requires the LEAST effort to be able to query this data?

   • AUse AWS Data Pipeline to transform the data and Amazon RDS to run queries.
   • BUse AWS Glue to catalogue the data and Amazon Athena to run queries.
   • CUse AWS Batch to run ETL on the data and Amazon Aurora to run the queries.
   • DUse AWS Lambda to transform the data and Amazon Kinesis Data Analytics to run queries.

   Show answer

   Answer: B

   Explanation

   The correct answer HAS TO be B Using Glue Use AWS Glue to catalogue the data and Amazon Athena to run queries against data on S3 are very typical use cases for those services. D is not ideal, Lambda can surely do many things but it requires development/testing effort, and Amazon Kinesis Data Analytics is not ideal for ad-hoc queries.

   Source: Adapted from community discussion — dhs227

   References

   • AWS documentation

   Next question

8. Question 348 · 368 in bank

   A credit card company wants to build a credit scoring model to help predict whether a new credit card applicant will default on a credit card payment. The company has collected data from a large number of sources with thousands of raw attributes. Early experiments to train a classification model revealed that many attributes are highly correlated, the large number of features slows down the training speed significantly, and that there are some overfitting issues. The Data Scientist on this project would like to speed up the model training time without losing a lot of information from the original dataset. Which feature engineering technique should the Data Scientist use to meet the objectives?

   • ARun self-correlation on all features and remove highly correlated features
   • BNormalize all numerical values to be between 0 and 1
   • CUse an autoencoder or principal component analysis (PCA) to replace original features with new features
   • DCluster raw data using k-means and use sample data from each cluster to build a new dataset

   Show answer

   Answer: C

   Explanation

   Answer is A, because one must avoid information loss that PCA or autoencoders introduce through new features (https://www.i2tutorials.com/what-are-the-pros-and-cons-of-the-pca/). Otherwise, I would perform C.

   Source: Adapted from community discussion — [Removed]

   Next question

9. Question 349 · 368 in bank

   A Data Scientist is training a multilayer perception (MLP) on a dataset with multiple classes. The target class of interest is unique compared to the other classes within the dataset, but it does not achieve and acceptable recall metric. The Data Scientist has already tried varying the number and size of the MLP's hidden layers, which has not significantly improved the results. A solution to improve recall must be implemented as quickly as possible. Which techniques should be used to meet these requirements?

   • AGather more data using Amazon Mechanical Turk and then retrain
   • BTrain an anomaly detection model instead of an MLP
   • CTrain an XGBoost model instead of an MLP
   • DAdd class weights to the MLP's loss function and then retrain

   Show answer

   Answer: D

   Explanation

   For me answer is D, adjust to higher weight for class of interest: https://androidkt.com/set-class-weight-for-imbalance-dataset-in-keras/. More data may/may not be available and a data labeling job will take time.

   Source: Adapted from community discussion — [Removed]

   Next question

10. Question 350 · 368 in bank

    A Machine Learning Specialist works for a credit card processing company and needs to predict which transactions may be fraudulent in near-real time. Specifically, the Specialist must train a model that returns the probability that a given transaction may fraudulent. How should the Specialist frame this business problem?

    • AStreaming classification
    • BBinary classification
    • CMulti-category classification
    • DRegression classification

    Show answer

    Answer: B

    Explanation

    there is nothing like regression classification. (instead it should have said logistic regression). It should be Binary. i.e., either fraud or non fraud. Even with probabilities, we have a threshold to decide the class.

    Source: Adapted from community discussion — srinu3054

    Next question

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

MLS-C01 practice, question 341. 368 questions available.