MLS-C01 practice questions 81–90

1. Question 81 · 368 in bank

   A data scientist has a dataset of machine part images stored in Amazon Elastic File System (Amazon EFS). The data scientist needs to use Amazon SageMaker to create and train an image classification machine learning model based on this dataset. Because of budget and time constraints, management wants the data scientist to create and train a model with the least number of steps and integration work required. How should the data scientist meet these requirements?

   • AMount the EFS file system to a SageMaker notebook and run a script that copies the data to an Amazon FSx for Lustre file system. Run the SageMaker training job with the FSx for Lustre file system as the data source.
   • BLaunch a transient Amazon EMR cluster. Configure steps to mount the EFS file system and copy the data to an Amazon S3 bucket by using S3DistCp. Run the SageMaker training job with Amazon S3 as the data source.
   • CMount the EFS file system to an Amazon EC2 instance and use the AWS CLI to copy the data to an Amazon S3 bucket. Run the SageMaker training job with Amazon S3 as the data source.
   • DRun a SageMaker training job with an EFS file system as the data source.

   Show answer

   Answer: D

   Explanation

   “When you create a training job, you specify the location of a training dataset and an input mode for accessing the dataset. For data location, Amazon SageMaker supports Amazon Simple Storage Service (Amazon S3), Amazon Elastic File System (Amazon EFS), and Amazon FSx for Lustre. ” https://docs.aws.amazon.com/sagemaker/latest/dg/model-access-training-data.html

   Source: Adapted from community discussion — Jerry84

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

2. Question 82 · 368 in bank

   A retail company uses a machine learning (ML) model for daily sales forecasting. The company's brand manager reports that the model has provided inaccurate results for the past 3 weeks. At the end of each day, an AWS Glue job consolidates the input data that is used for the forecasting with the actual daily sales data and the predictions of the model. The AWS Glue job stores the data in Amazon S3. The company's ML team is using an Amazon SageMaker Studio notebook to gain an understanding about the source of the model's inaccuracies. What should the ML team do on the SageMaker Studio notebook to visualize the model's degradation MOST accurately?

   • ACreate a histogram of the daily sales over the last 3 weeks. In addition, create a histogram of the daily sales from before that period.
   • BCreate a histogram of the model errors over the last 3 weeks. In addition, create a histogram of the model errors from before that period.
   • CCreate a line chart with the weekly mean absolute error (MAE) of the model.
   • DCreate a scatter plot of daily sales versus model error for the last 3 weeks. In addition, create a scatter plot of daily sales versus model error from before that period.

   Show answer

   Answer: C

   Explanation

   C is correct. We could view the "Degradation" as a trend. Line charts are usually very helpful to show if there is any trend in the data over the period of time under analysis. Histogram is normally used to visualizing distributions in your data.

   Source: Adapted from community discussion — Jerry84

   References

   • AWS documentation

   Next question

3. Question 83 · 368 in bank

   An ecommerce company sends a weekly email newsletter to all of its customers. Management has hired a team of writers to create additional targeted content. A data scientist needs to identify five customer segments based on age, income, and location. The customers' current segmentation is unknown. The data scientist previously built an XGBoost model to predict the likelihood of a customer responding to an email based on age, income, and location. Why does the XGBoost model NOT meet the current requirements, and how can this be fixed?

   • AThe XGBoost model provides a true/false binary output. Apply principal component analysis (PCA) with five feature dimensions to predict a segment.
   • BThe XGBoost model provides a true/false binary output. Increase the number of classes the XGBoost model predicts to five classes to predict a segment.
   • CThe XGBoost model is a supervised machine learning algorithm. Train a k-Nearest-Neighbors (kNN) model with K = 5 on the same dataset to predict a segment.
   • DThe XGBoost model is a supervised machine learning algorithm. Train a k-means model with K = 5 on the same dataset to predict a segment.

   Show answer

   Answer: D

   Explanation

   The answer is D. 1. "The current segmentation of consumers is unclear." so it is unsupervised learning. 2. Then K-means is for unsupervised learning.

   Source: Adapted from community discussion — tgaos

   Next question

4. Question 84 · 368 in bank

   A global financial company is using machine learning to automate its loan approval process. The company has a dataset of customer information. The dataset contains some categorical fields, such as customer location by city and housing status. The dataset also includes financial fields in different units, such as account balances in US dollars and monthly interest in US cents. The company's data scientists are using a gradient boosting regression model to infer the credit score for each customer. The model has a training accuracy of 99% and a testing accuracy of 75%. The data scientists want to improve the model's testing accuracy. Which process will improve the testing accuracy the MOST?

   • AUse a one-hot encoder for the categorical fields in the dataset. Perform standardization on the financial fields in the dataset. Apply L1 regularization to the data.
   • BUse tokenization of the categorical fields in the dataset. Perform binning on the financial fields in the dataset. Remove the outliers in the data by using the z- score.
   • CUse a label encoder for the categorical fields in the dataset. Perform L1 regularization on the financial fields in the dataset. Apply L2 regularization to the data.
   • DUse a logarithm transformation on the categorical fields in the dataset. Perform binning on the financial fields in the dataset. Use imputation to populate missing values in the dataset.

   Show answer

   Answer: A

   Explanation

   A: it's overfitting so regularization is needed, need apply scaling on financial data fields as it's for regression problem; one hot encoding for city of the house field.

   Source: Adapted from community discussion — spaceexplorer

   Next question

5. Question 85 · 368 in bank

   Select 2

   A machine learning (ML) specialist needs to extract embedding vectors from a text series. The goal is to provide a ready-to-ingest feature space for a data scientist to develop downstream ML predictive models. The text consists of curated sentences in English. Many sentences use similar words but in different contexts. There are questions and answers among the sentences, and the embedding space must differentiate between them. Which options can produce the required embedding vectors that capture word context and sequential QA information? (Choose two.)

   • AAmazon SageMaker seq2seq algorithm
   • BAmazon SageMaker BlazingText algorithm in Skip-gram mode
   • CAmazon SageMaker Object2Vec algorithm
   • DAmazon SageMaker BlazingText algorithm in continuous bag-of-words (CBOW) mode
   • ECombination of the Amazon SageMaker BlazingText algorithm in Batch Skip-gram mode with a custom recurrent neural network (RNN)

   Show answer

   Answer: AC

   Explanation

   seq2seq and object2vec take care of more than just the words. Any response with blazingText is wrong because blazingText just uses a cbow (continuous bag of words), working only on individual words

   Source: Adapted from community discussion — ovokpus

   References

   • AWS documentation
   • AWS documentation

   Next question

6. Question 86 · 368 in bank

   A retail company wants to update its customer support system. The company wants to implement automatic routing of customer claims to different queues to prioritize the claims by category. Currently, an operator manually performs the category assignment and routing. After the operator classifies and routes the claim, the company stores the claim's record in a central database. The claim's record includes the claim's category. The company has no data science team or experience in the field of machine learning (ML). The company's small development team needs a solution that requires no ML expertise. Which solution meets these requirements?

   • AExport the database to a .csv file with two columns: claim_label and claim_text. Use the Amazon SageMaker Object2Vec algorithm and the .csv file to train a model. Use SageMaker to deploy the model to an inference endpoint. Develop a service in the application to use the inference endpoint to process incoming claims, predict the labels, and route the claims to the appropriate queue.
   • BExport the database to a .csv file with one column: claim_text. Use the Amazon SageMaker Latent Dirichlet Allocation (LDA) algorithm and the .csv file to train a model. Use the LDA algorithm to detect labels automatically. Use SageMaker to deploy the model to an inference endpoint. Develop a service in the application to use the inference endpoint to process incoming claims, predict the labels, and route the claims to the appropriate queue.
   • CUse Amazon Textract to process the database and automatically detect two columns: claim_label and claim_text. Use Amazon Comprehend custom classification and the extracted information to train the custom classifier. Develop a service in the application to use the Amazon Comprehend API to process incoming claims, predict the labels, and route the claims to the appropriate queue.
   • DExport the database to a .csv file with two columns: claim_label and claim_text. Use Amazon Comprehend custom classification and the .csv file to train the custom classifier. Develop a service in the application to use the Amazon Comprehend API to process incoming claims, predict the labels, and route the claims to the appropriate queue.

   Show answer

   Answer: D

   Explanation

   A. NO - Object2Vec is unsupervised, it will create vector representations but not assign to a category the claims B. NO - we want a supervised method, LDA will create topics in an unsupervised way C. NO - again we want a supervised method D. YES - That is supervised; no need for ML skills, only basic API programming

   Source: Adapted from community discussion — loict

   References

   • AWS documentation

   Next question

7. Question 87 · 368 in bank

   A machine learning (ML) specialist is using Amazon SageMaker hyperparameter optimization (HPO) to improve a model's accuracy. The learning rate parameter is specified in the following HPO configuration:

   

   During the results analysis, the ML specialist determines that most of the training jobs had a learning rate between 0.01 and 0.1. The best result had a learning rate of less than 0.01. Training jobs need to run regularly over a changing dataset. The ML specialist needs to find a tuning mechanism that uses different learning rates more evenly from the provided range between MinValue and MaxValue. Which solution provides the MOST accurate result?

   • AModify the HPO configuration as follows: Select the most accurate hyperparameter configuration form this HPO job.
   • BRun three different HPO jobs that use different learning rates form the following intervals for MinValue and MaxValue while using the same number of training jobs for each HPO job: ✑ [0.01, 0.1] ✑ [0.001, 0.01] ✑ [0.0001, 0.001] Select the most accurate hyperparameter configuration form these three HPO jobs.
   • CModify the HPO configuration as follows: Select the most accurate hyperparameter configuration form this training job.
   • DRun three different HPO jobs that use different learning rates form the following intervals for MinValue and MaxValue. Divide the number of training jobs for each HPO job by three: ✑ [0.01, 0.1] ✑ [0.001, 0.01] [0.0001, 0.001] Select the most accurate hyperparameter configuration form these three HPO jobs.

   Show answer

   Answer: C

   Explanation

   "Choose logarithmic scaling when you are searching a range that spans several orders of magnitude. For example, if you are tuning a Tune a linear learner model model, and you specify a range of values between .0001 and 1.0 for the learning_rate hyperparameter, searching uniformly on a logarithmic scale gives you a better sample of the entire range than searching on a linear scale would, because searching on a linear scale would, on average, devote 90 percent of your training budget to only the values between .1 and 1.0, leaving only 10 percent of your training budget for the values between .0001 and .1." based on the above from this link https://docs.aws.amazon.com/sagemaker/latest/dg/automatic-model-tuning-define-ranges.html C is clearly the answer

   Source: Adapted from community discussion — ovokpus

   References

   • AWS documentation

   Next question

8. Question 88 · 368 in bank

   A manufacturing company wants to use machine learning (ML) to automate quality control in its facilities. The facilities are in remote locations and have limited internet connectivity. The company has 20 ׀¢׀’ of training data that consists of labeled images of defective product parts. The training data is in the corporate on- premises data center. The company will use this data to train a model for real-time defect detection in new parts as the parts move on a conveyor belt in the facilities. The company needs a solution that minimizes costs for compute infrastructure and that maximizes the scalability of resources for training. The solution also must facilitate the company's use of an ML model in the low-connectivity environments. Which solution will meet these requirements?

   • AMove the training data to an Amazon S3 bucket. Train and evaluate the model by using Amazon SageMaker. Optimize the model by using SageMaker Neo. Deploy the model on a SageMaker hosting services endpoint.
   • BTrain and evaluate the model on premises. Upload the model to an Amazon S3 bucket. Deploy the model on an Amazon SageMaker hosting services endpoint.
   • CMove the training data to an Amazon S3 bucket. Train and evaluate the model by using Amazon SageMaker. Optimize the model by using SageMaker Neo. Set up an edge device in the manufacturing facilities with AWS IoT Greengrass. Deploy the model on the edge device.
   • DTrain the model on premises. Upload the model to an Amazon S3 bucket. Set up an edge device in the manufacturing facilities with AWS IoT Greengrass. Deploy the model on the edge device.

   Show answer

   Answer: C

   Explanation

   Moving the training data to an Amazon S3 bucket and training and evaluating the model by using Amazon SageMaker will reduce the company's compute infrastructure costs and maximize the scalability of resources for training. Optimizing the model by using SageMaker Neo will further reduce costs by allowing the model to run on inexpensive edge devices. Setting up an edge device in the manufacturing facilities with AWS IoT Greengrass and deploying the model on the edge device will enable the company to use the ML model in the low-connectivity environments. This solution provides a complete end-to-end solution for the company's needs, from data storage to model deployment, while minimizing costs and providing scalability and offline capabilities.

   Source: Adapted from community discussion — AjoseO

   Next question

9. Question 89 · 368 in bank

   A Machine Learning Specialist is packaging a custom ResNet model into a Docker container so the company can leverage Amazon SageMaker for training. The Specialist is using Amazon EC2 P3 instances to train the model and needs to properly configure the Docker container to leverage the NVIDIA GPUs. What does the Specialist need to do?

   • ABundle the NVIDIA drivers with the Docker image.
   • BBuild the Docker container to be NVIDIA-Docker compatible.
   • COrganize the Docker container's file structure to execute on GPU instances.
   • DSet the GPU flag in the Amazon SageMaker CreateTrainingJob request body.

   Show answer

   Answer: B

   Explanation

   https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-dg.pdf page 55: If you plan to use GPU devices, make sure that your containers are nvidia-docker compatible. Only the CUDA toolkit should be included on containers. Don't bundle NVIDIA drivers with the image. For more information about nvidia-docker, see NVIDIA/nvidia-docker. So the answer is B

   Source: Adapted from community discussion — vetal

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

10. Question 90 · 368 in bank

    Select 2

    A company has an ecommerce website with a product recommendation engine built in TensorFlow. The recommendation engine endpoint is hosted by Amazon SageMaker. Three compute-optimized instances support the expected peak load of the website. Response times on the product recommendation page are increasing at the beginning of each month. Some users are encountering errors. The website receives the majority of its traffic between 8 AM and 6 PM on weekdays in a single time zone. Which of the following options are the MOST effective in solving the issue while keeping costs to a minimum? (Choose two.)

    • AConfigure the endpoint to use Amazon Elastic Inference (EI) accelerators.
    • BCreate a new endpoint configuration with two production variants.
    • CConfigure the endpoint to automatically scale with the InvocationsPerInstance metric.
    • DDeploy a second instance pool to support a blue/green deployment of models.
    • EReconfigure the endpoint to use burstable instances.

    Show answer

    Answer: AC

    Explanation

    Interesting if option A will be relevant anymore, as AWS is discontinuing Elastic Inference starting Apr 15. https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html. Wonder if they change the option to include Inf instane type

    Source: Adapted from community discussion — luckybme

    References

    • 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 81. 368 questions available.