AWS Machine Learning Certification - Quiz #4

Created on June 03, 2020 By

admin

AWS Machine Learning – Quiz 4

1 / 8

QUESTION

A product owner is working with a data science team who use Spark on AWS EMR for big data projects and have significant expertise with Spark. They have indicated a preference to work with Spark + MLLib to address the real-time predictions use case you’ve proposed.

Which of the following would you recommend as the most scalable and efficient way to proceed?

Use Spark for ETL, SageMaker to train & deploy models

Build a Spark Pipeline to including ETL and model training. Deploy via the Spark cluster

Use Spark for Model development, then deploy via SageMaker

Use Spark for ETL and to train a model, MLEAP Serialisation to deploy into SageMaker

2 / 8

QUESTION

The development team want to make use of SageMaker auto-scaling. Where should this be configured?

(Select One?)

In the model, edit the instance type and add auto-scaling parameters

In the endpoint configuration – add auto-scaling policy

In the endpoint itself – configure the auto-scaling policy

ConfigureSageMaker auto-scaling directly in CloudWatch

3 / 8

QUESTION

A data scientist has been experimenting with a deep neural network, utilising Kaggle’s free Jupyter notebook environment, Keras and Tensorflow.

Which of the options corresponds to the minimal actions needed to get this running on SageMaker?

(Select One)

a. Load train & test data into S3
b. Modify your Kaggle Script to accept model directory, train and test, host arguments and to save the model
c. Add your Kaggle script (myscript.py) into your Notebook instance
d. Register Your Container on ECM
e. Specify the Container location in the SageMaker estimator.
f. Create a SageMaker notebook and use myscript.py as the entry point in the TensorFlow estimator.
g. Use SageMaker Kaggle Sync to transfer the script file and model artifacts to S3.
h. Create a serve script

a, e, f, h

h, b, d, e

a, c, d, h

a,b,c,f

4 / 8

QUESTION

A product owner has made the development team aware of a number of built-in machine learning capabilities associated with various AWS Services. Match the machine learning capability with the AWS service.

a) Anomaly detection (RCF) + Hotspot detection
b) Duplicate detection (FindMatches ML)
c) Anomaly detection (RCF), Forecasting, Auto-Narratives
d) Active label learning

(Select One)

a) Amazon QuickSight, b) AWS Glue, c)Kinesis Data Analytics d) SageMaker – Ground Truth

a) AWS Glue b) Amazon QuickSight c) SageMaker – Ground Truth

a) Kinesis Data Analytics b) EMR Pipeline c) Amazon QuickSight d) SageMaker – Ground Truth

a) Kinesis Data Analytics , b) AWS Glue, c) Amazon QuickSight d) SageMaker – Ground Truth

5 / 8

QUESTION

A data & development team have built a deep learning model on a SageMaker TensorFlow Framework container. However, the model is performing poorly and training is frequently failing.

Which of the following approaches would help resolve the issue?

(Select One)

Manually print debug data and analyse that data

use open source tools for charting and refer to CloudWatch logs

add dropout layers and substitute tanh activation functions for relu

define rules via Sagemaker debugger, create hooks to save tensors to S3, use SageMaker Studio to visualise training issues.

6 / 8

QUESTION

A data scientist is utilising SageMaker notebooks to explore various machine learning models with a subset of the data. Which of the following are true?

(Select Two)

Pipe mode should be used so that the notebook instance launches faster and training completes more quickly

Use local mode where available to iterate and test work

Local mode is available for all SageMaker estimators

Local mode is available for Tensorflow and MXNet only

7 / 8

QUESTION

A developer is choosing between two different approaches for working with SageMaker – which of the following are true?

(Select Two)

SageMaker Python SDK provides finer grained control of SageMaker features than Boto3

Boto3 is recommended for production and automation work with SageMaker

SageMaker Python SDK provides several high-level abstractions for working with SageMaker including Estimators, Models, Predictors, Session, Transformers, Processors

Unlike SageMaker Python SDK, Boto3 is available in languages other than Python, such as R

8 / 8

QUESTION

Which of the following must be set by the user (required hyperparameters), for SageMaker’s built-in algorithm, Linear Learner? (assume classification)

(Select Two)

feature_dim

num_classes

predictor_type

epochs

Your score is

The average score is 43%

0%

AWS Machine Learning Certification – Quiz #4

No responses yet

Leave a Reply Cancel reply