MLS-C01 practice questions 191–200

1. Question 191 · 368 in bank

   A medical device company is building a machine learning (ML) model to predict the likelihood of device recall based on customer data that the company collects from a plain text survey. One of the survey questions asks which medications the customer is taking. The data for this field contains the names of medications that customers enter manually. Customers misspell some of the medication names. The column that contains the medication name data gives a categorical feature with high cardinality but redundancy. What is the MOST effective way to encode this categorical feature into a numeric feature?

   • ASpell check the column. Use Amazon SageMaker one-hot encoding on the column to transform a categorical feature to a numerical feature.
   • BFix the spelling in the column by using char-RNN. Use Amazon SageMaker Data Wrangler one-hot encoding to transform a categorical feature to a numerical feature.
   • CUse Amazon SageMaker Data Wrangler similarity encoding on the column to create embeddings of vectors of real numbers.
   • DUse Amazon SageMaker Data Wrangler ordinal encoding on the column to encode categories into an integer between 0 and the total number of categories in the column.

   Show answer

   Answer: C

   Explanation

   The similarity encoder creates embeddings for columns with categorical data. An embedding is a mapping of discrete objects, such as words, to vectors of real numbers. It encodes similar strings to vectors containing similar values. For example, it creates very similar encodings for "California" and "Calfornia". https://docs.aws.amazon.com/sagemaker/latest/dg/data-wrangler-transform.html

   Source: Adapted from community discussion — Topg4u

   References

   • AWS documentation

   Next question

2. Question 192 · 368 in bank

   Select 2

   A machine learning (ML) engineer has created a feature repository in Amazon SageMaker Feature Store for the company. The company has AWS accounts for development, integration, and production. The company hosts a feature store in the development account. The company uses Amazon S3 buckets to store feature values offline. The company wants to share features and to allow the integration account and the production account to reuse the features that are in the feature repository. Which combination of steps will meet these requirements? (Choose two.)

   • ACreate an IAM role in the development account that the integration account and production account can assume. Attach IAM policies to the role that allow access to the feature repository and the S3 buckets.
   • BShare the feature repository that is associated the S3 buckets from the development account to the integration account and the production account by using AWS Resource Access Manager (AWS RAM).
   • CUse AWS Security Token Service (AWS STS) from the integration account and the production account to retrieve credentials for the development account.
   • DSet up S3 replication between the development S3 buckets and the integration and production S3 buckets.
   • ECreate an AWS PrivateLink endpoint in the development account for SageMaker.

   Show answer

   Answer: AB

   Explanation

   A: By creating an IAM role in the development account that the integration and production accounts can assume, you establish a trust relationship between the accounts. You can attach IAM policies to the role that grant the necessary permissions to access the feature repository and S3 buckets. B: AWS Resource Access Manager (AWS RAM) enables resource sharing across AWS accounts. By sharing the feature repository associated with the S3 buckets using AWS RAM, you allow the integration and production accounts to access and reuse the features.

   Source: Adapted from community discussion — xiaoeason

   References

   • AWS documentation

   Next question

3. Question 193 · 368 in bank

   A data scientist for a medical diagnostic testing company has developed a machine learning (ML) model to identify patients who have a specific disease. The dataset that the scientist used to train the model is imbalanced. The dataset contains a large number of healthy patients and only a small number of patients who have the disease. The model should consider that patients who are incorrectly identified as positive for the disease will increase costs for the company. Which metric will MOST accurately evaluate the performance of this model?

   • ARecall
   • BF1 score
   • CAccuracy
   • DPrecision

   Show answer

   Answer: D

   Explanation

   We want to give more weight to the “FP” error, so we need to keep an eye on Letter D: Precision. Letter D is correct. F1-Score gives the same weight for Recall and Precision, so it's wrong (given the question statement)

   Source: Adapted from community discussion — kaike_reis

   Next question

4. Question 194 · 368 in bank

   A wildlife research company has a set of images of lions and cheetahs. The company created a dataset of the images. The company labeled each image with a binary label that indicates whether an image contains a lion or cheetah. The company wants to train a model to identify whether new images contain a lion or cheetah. Which Amazon SageMaker algorithm will meet this requirement?

   • AXGBoost
   • BImage Classification - TensorFlow
   • CObject Detection - TensorFlow
   • DSemantic segmentation - MXNet

   Show answer

   Answer: B

   Explanation

   Image Classification - TensorFlow is a built-in algorithm in Amazon SageMaker that can be used to train a model to identify images of lions and cheetahs. The algorithm uses a convolutional neural network (CNN) to extract features from the images and then classifies the images based on the features

   Source: Adapted from community discussion — Mickey321

   Next question

5. Question 195 · 368 in bank

   A company is building a new supervised classification model in an AWS environment. The company's data science team notices that the dataset has a large quantity of variables. All the variables are numeric. The model accuracy for training and validation is low. The model's processing time is affected by high latency. The data science team needs to increase the accuracy of the model and decrease the processing time. What should the data science team do to meet these requirements?

   • ACreate new features and interaction variables.
   • BUse a principal component analysis (PCA) model.
   • CApply normalization on the feature set.
   • DUse a multiple correspondence analysis (MCA) model.

   Show answer

   Answer: B

   Explanation

   B. Use a principal component analysis (PCA) model. This is because PCA can help to reduce the number of variables while preserving the most important information, which can help to improve the accuracy of the model and reduce the processing time.

   Source: Adapted from community discussion — usamazubairi

   Next question

6. Question 196 · 368 in bank

   An exercise analytics company wants to predict running speeds for its customers by using a dataset that contains multiple health-related features for each customer. Some of the features originate from sensors that provide extremely noisy values. The company is training a regression model by using the built-in Amazon SageMaker linear learner algorithm to predict the running speeds. While the company is training the model, a data scientist observes that the training loss decreases to almost zero, but validation loss increases. Which technique should the data scientist use to optimally fit the model?

   • AAdd L1 regularization to the linear learner regression model.
   • BPerform a principal component analysis (PCA) on the dataset. Use the linear learner regression model.
   • CPerform feature engineering by including quadratic and cubic terms. Train the linear learner regression model.
   • DAdd L2 regularization to the linear learner regression model.

   Show answer

   Answer: A

   Explanation

   If you suspect that some features are irrelevant, Option A (L1 Regularization) could be more effective as it can shrink some coefficients to zero, effectively performing feature selection be removing the noise. If you believe that most features are relevant but the model is too complex, Option D (L2 Regularization) is typically the better choice as it evenly shrinks all coefficients, thus reducing model complexity without eliminating features. In this case, option A would be ideal to get rid of the irrelevant noise.

   Source: Adapted from community discussion — CloudHandsOn

   References

   • AWS documentation

   Next question

7. Question 197 · 368 in bank

   A company is planning a marketing campaign to promote a new product to existing customers. The company has data for past promotions that are similar. The company decides to try an experiment to send a more expensive marketing package to a smaller number of customers. The company wants to target the marketing campaign to customers who are most likely to buy the new product. The experiment requires that at least 90% of the customers who are likely to purchase the new product receive the marketing materials. The company trains a model by using the linear learner algorithm in Amazon SageMaker. The model has a recall score of 80% and a precision of 75%. How should the company retrain the model to meet these requirements?

   • ASet the target_recall hyperparameter to 90%. Set the binary_classifier_model_selection_criteria hyperparameter to recall_at_target_precision.
   • BSet the target_precision hyperparameter to 90%. Set the binary_classifier_model_selection_criteria hyperparameter to precision_at_target_recall.
   • CUse 90% of the historical data for training. Set the number of epochs to 20.
   • DSet the normalize_label hyperparameter to true. Set the number of classes to 2.

   Show answer

   Answer: A

   Explanation

   For classification problems, such as the one here, you can specify the binary_classifier_model_selection_criteria hyperparameter to control how the best model is selected from the validation set. You can choose from several criteria, such as accuracy, precision, recall, F1 measure, or cross-entropy loss1.

   Source: Adapted from community discussion — Mickey321

   Next question

8. Question 198 · 368 in bank

   Select 2

   A company's machine learning (ML) specialist is building a computer vision model to classify 10 different traffic signs. The company has stored 100 images of each class in Amazon S3, and the company has another 10,000 unlabeled images. All the images come from dash cameras and are a size of 224 pixels × 224 pixels. After several training runs, the model is overfitting on the training data. Which actions should the ML specialist take to address this problem? (Choose two.)

   • AUse Amazon SageMaker Ground Truth to label the unlabeled images.
   • BUse image preprocessing to transform the images into grayscale images.
   • CUse data augmentation to rotate and translate the labeled images.
   • DReplace the activation of the last layer with a sigmoid.
   • EUse the Amazon SageMaker k-nearest neighbors (k-NN) algorithm to label the unlabeled images.

   Show answer

   Answer: AC

   Explanation

   C. Use data augmentation to rotate and translate the labeled images. Data augmentation involves creating new training data by applying transformations such as rotation, translation, scaling, etc. This helps to increase the diversity of the training data and makes the model more robust without requiring additional labeled data. A. Use Amazon SageMaker Ground Truth to label the unlabeled images. Leveraging Amazon SageMaker Ground Truth can help in labeling the unlabeled images to expand the training dataset and reduce overfitting. Adding more labeled data can improve the generalization of the model and reduce overfitting.

   Source: Adapted from community discussion — xiaoeason

   Next question

9. Question 199 · 368 in bank

   A data science team is working with a tabular dataset that the team stores in Amazon S3. The team wants to experiment with different feature transformations such as categorical feature encoding. Then the team wants to visualize the resulting distribution of the dataset. After the team finds an appropriate set of feature transformations, the team wants to automate the workflow for feature transformations. Which solution will meet these requirements with the MOST operational efficiency?

   • AUse Amazon SageMaker Data Wrangler preconfigured transformations to explore feature transformations. Use SageMaker Data Wrangler templates for visualization. Export the feature processing workflow to a SageMaker pipeline for automation.
   • BUse an Amazon SageMaker notebook instance to experiment with different feature transformations. Save the transformations to Amazon S3. Use Amazon QuickSight for visualization. Package the feature processing steps into an AWS Lambda function for automation.
   • CUse AWS Glue Studio with custom code to experiment with different feature transformations. Save the transformations to Amazon S3. Use Amazon QuickSight for visualization. Package the feature processing steps into an AWS Lambda function for automation.
   • DUse Amazon SageMaker Data Wrangler preconfigured transformations to experiment with different feature transformations. Save the transformations to Amazon S3. Use Amazon QuickSight for visualization. Package each feature transformation step into a separate AWS Lambda function. Use AWS Step Functions for workflow automation.

   Show answer

   Answer: A

   Explanation

   This solution offers the following advantages: Amazon SageMaker Data Wrangler provides a user-friendly interface to explore and experiment with feature transformations, making it efficient for the data science team to try out different options. SageMaker Data Wrangler templates for visualization can quickly generate visualizations for the resulting distribution of the dataset, streamlining the visualization process. Exporting the feature processing workflow to a SageMaker pipeline for automation automates the feature transformations efficiently within the SageMaker environment.

   Source: Adapted from community discussion — xiaoeason

   Next question

10. Question 200 · 368 in bank

    A company is using Amazon Polly to translate plaintext documents to speech for automated company announcements. However, company acronyms are being mispronounced in the current documents. How should a Machine Learning Specialist address this issue for future documents?

    • AConvert current documents to SSML with pronunciation tags.
    • BCreate an appropriate pronunciation lexicon.
    • COutput speech marks to guide in pronunciation.
    • DUse Amazon Lex to preprocess the text files for pronunciation

    Show answer

    Answer: B

    Explanation

    SSML is specific to that particular doument, like W3C an be pronounced as "World Wide Web Consortium" using W3C in that specific document and when you create a new document, you need to format again. But with LEXICONS, you can upload a lexicon file once and ALL the FUTURE documents can just have W3C and that will be pronounced as "World Wide Web Consortium".. so answer is B, because the question asks for "future" documents.

    Source: Adapted from community discussion — VB

    References

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

    Next question

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

MLS-C01 practice, question 191. 368 questions available.