MLOps on AWS, Azure and GCP — Free Practice Questions

Q: True or False. If you have mission critical data that must be processed with as minimal delay as possible, you should use the Kinesis API (AWS SDK) over the Kinesis Producer Library.

Correct answer: True. The KPL can incur an additional processing delay of up to RecordMaxBufferedTime within the library (user-configurable). Larger values of RecordMaxBufferedTime results in higher packing efficiencies and better performance. Applications that cannot tolerate this additional delay may need to use the AWS SDK directly.

Q: What are your options for storing data into S3?

Correct answer: AWS CLI; AWS SDK; The AWS console. You can use the AWS console, the AWS command line interface (cli), or the AWS SDK. You can use the AWS console, the AWS command line interface (cli), or the AWS SDK. You can use the AWS console, the AWS command line interface (cli), or the AWS SDK.

Q: You have been tasked with using Polly to translate text to speech in the company announcements that launch weekly. The problem you are encountering is how Polly is incorrectly translating the companies acronyms. What can be done for future tasks to help prevent this?

Correct answer: Use SSML tags in documents; Create dictionary lexicon. Using SSML-enhanced input text gives you additional control over how Amazon Polly generates speech from the text you provide. Using these tags allows you to substitute a different word (or pronunciation) for selected text such as an acronym or abbreviation. You can also create a dictionary lexicon to apply to any future tasks instead of apply SSML to each individual document. Using SSML-enhanced input text gives you additional control over how Amazon Polly generates speech from the text you provide. Using these tags allows you to substitute a different word (or pronunciation) for selected text such as an acronym or abbreviation. You can also create a dictionary lexicon to apply to any future tasks instead of apply SSML to each individual document.

Q: Accurate labels are necessary to properly train supervised models. Many times, human subjects known as raters perform this labeling effort. What are the main categories of human raters? (check all that apply).

Correct answer: Subject matter experts; Your users. Generalists usually come from crowdsourcing sites. SME or subject matter experts : classical example is radiologists labeling medical images for automated diagnosis tools. Users can provide labels within your application. A classical example is photo tagging. Generalists usually come from crowdsourcing sites. SME or subject matter experts : classical example is radiologists labeling medical images for automated diagnosis tools. Users can provide labels within your application. A classical example is photo tagging.

Q: A cardiologist labeling MRI images is a typical example of Direct Labeling.

Correct answer: False. MRI labeling by a medical specialist is an example of Human Labeling and not Direct Labeling.

Q: Distribution skew occurs when the distribution of the training dataset is significantly different from the distribution of the serving dataset, and is typically caused by: (check all that apply).

Correct answer: Faulty sampling method that selects a sample for training which is not representative of serving data distribution.; Different data sources for training and serving data.; Trend, seasonality, changes in data over time.. Distribution Skew example : 1) A faulty sampling mechanism that chooses a non-representative subsample is an example of distribution skew. 2) Data sources between training and serving often change and so this is another case of distribution skew. 3) Data distributions between training and serving often change and so this is another case of distribution skew. Distribution Skew example : 1) A faulty sampling mechanism that chooses a non-representative subsample is an example of distribution skew. 2) Data sources between training and serving often change and so this is another case of distribution skew. 3) Data distributions between training and serving often change and so this is another case of distribution skew. Distribution Skew example : 1) A faulty sampling mechanism that chooses a non-representative subsample is an example of distribution skew. 2) Data sources between training and serving often change and so this is another case of distribution s

Q: TensorFlow Data Validation (TFDV) helps TFX users maintain the health of their ML pipelines. TFDV can analyze training and serves data to:

Correct answer: Compute descriptive statistics.; Detect data anomalies.; Infer a schema.. TensorFlow Data Validation (TFDV) performs Descriptive Statistics , Infer a schema and Anomaly Detection. It does not perform Feature Engineering or Selection. Deployment on mobile device is done by TensorFlow Lite. TensorFlow Data Validation (TFDV) performs Descriptive Statistics , Infer a schema and Anomaly Detection. It does not perform Feature Engineering or Selection. Deployment on mobile device is done by TensorFlow Lite. TensorFlow Data Validation (TFDV) performs Descriptive Statistics , Infer a schema and Anomaly Detection. It does not perform Feature Engineering or Selection. Deployment on mobile device is done by TensorFlow Lite.

Q: We want to deploy an AI app that collects user data in different Azure regions. We want to ensure data stays in the region of origin. Which three of the following would we deploy to each region?

Correct answer: The application itself.; An Azure Storage resource.; The Cognitive Services resources.. Using an instance of the app in each region would allow each instance to access data only within its own region. Deploying the Cognitive Services resources in each region will facilitate access to data in storage accounts in the same region. Azure Storage can be deployed to each region, and therefore the data stored within is constrained to stay within that region as long as the app tier does not redistribute queried data. Using an instance of the app in each region would allow each instance to access data only within its own region. Deploying the Cognitive Services resources in each region will facilitate access to data in storage accounts in the same region. Azure Storage can be deployed to each region, and therefore the data stored within is constrained to stay within that region as long as the app tier does not redistribute queried data. Using an instance of the app in each region would allow each instance to access data only within its own region. Deploying the Cognitive Services resources in each region will facilitate access to data in storage accounts in the same region.

Question 1

1. True or False. If you have mission critical data that must be processed with as minimal delay as possible, you should use the Kinesis API (AWS SDK) over the Kinesis Producer Library.

✓True
The KPL can incur an additional processing delay of up to RecordMaxBufferedTime within the library (user-configurable). Larger values of RecordMaxBufferedTime results in higher packing efficiencies and better performance. Applications that cannot tolerate this additional delay may need to use the AWS SDK directly.
✗False

Question 2

2. What are your options for storing data into S3?

✗UPLOAD command
✓AWS CLI
You can use the AWS console, the AWS command line interface (cli), or the AWS SDK.
✗UNLOAD command
✓AWS SDK
✓The AWS console

Question 3

3. You have been tasked with using Polly to translate text to speech in the company announcements that launch weekly. The problem you are encountering is how Polly is incorrectly translating the companies acronyms. What can be done for future tasks to help prevent this?

✗Use Amazon Transcribe to first map the acronyms to pronunciations then include them in the Amazon polly pipeline
✗Use speech marks for input text documents
✓Use SSML tags in documents
Using SSML-enhanced input text gives you additional control over how Amazon Polly generates speech from the text you provide. Using these tags allows you to substitute a different word (or pronunciation) for selected text such as an acronym or abbreviation. You can also create a dictionary lexicon to apply to any future tasks instead of apply SSML to each individual document.
✓Create dictionary lexicon

Question 4

4. Accurate labels are necessary to properly train supervised models. Many times, human subjects known as raters perform this labeling effort. What are the main categories of human raters? (check all that apply).

✓Subject matter experts
Generalists usually come from crowdsourcing sites. SME or subject matter experts : classical example is radiologists labeling medical images for automated diagnosis tools. Users can provide labels within your application. A classical example is photo tagging.
✗Generalists
✗Aggregators
✓Your users

Question 5

5. A cardiologist labeling MRI images is a typical example of Direct Labeling.

✓False
MRI labeling by a medical specialist is an example of Human Labeling and not Direct Labeling.
✗True

Question 6

6. Distribution skew occurs when the distribution of the training dataset is significantly different from the distribution of the serving dataset, and is typically caused by: (check all that apply).

✓Faulty sampling method that selects a sample for training which is not representative of serving data distribution.
Distribution Skew example : 1) A faulty sampling mechanism that chooses a non-representative subsample is an example of distribution skew. 2) Data sources between training and serving often change and so this is another case of distribution skew. 3) Data distributions between training and serving often change and so this is another case of distribution skew.
✗There is different logic for generating features between training and serving. For example, if you apply some transformation only in one of the two code paths.
✓Different data sources for training and serving data.
✓Trend, seasonality, changes in data over time.

Question 7

7. TensorFlow Data Validation (TFDV) helps TFX users maintain the health of their ML pipelines. TFDV can analyze training and serves data to:

✗Deploy pipeline to a mobile application.
✓Compute descriptive statistics.
TensorFlow Data Validation (TFDV) performs Descriptive Statistics , Infer a schema and Anomaly Detection. It does not perform Feature Engineering or Selection. Deployment on mobile device is done by TensorFlow Lite.
✓Detect data anomalies.
✓Infer a schema.

Question 8

8. We want to deploy an AI app that collects user data in different Azure regions. We want to ensure data stays in the region of origin. Which three of the following would we deploy to each region?

✓The application itself.
Using an instance of the app in each region would allow each instance to access data only within its own region. Deploying the Cognitive Services resources in each region will facilitate access to data in storage accounts in the same region. Azure Storage can be deployed to each region, and therefore the data stored within is constrained to stay within that region as long as the app tier does not redistribute queried data.
✓An Azure Storage resource.
✗Azure Kubernetes Service (AKS).
✓The Cognitive Services resources.

MLOps on AWS, Azure and GCP — Free Practice Questions

Topics covered

Sample questions with answers