Brainscape's Knowledge GenomeTM


Top Flashcards (Certified)
All Flashcards

AWS AI Practitioner Exam > AWS Managed AI Services > Flashcards

AWS Managed AI Services Flashcards

1
Q

What AWS services are used for text and document processing?

A

Amazon Comprehend, Amazon Translate, Amazon Textract.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What AWS service is used for image and video analysis?

A

Amazon Rekognition.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What AWS service is used for search?

A

Amazon Kendra.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What AWS service is used for building chatbots?

A

Amazon Lex.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What AWS services are used for speech processing?

A

Amazon Polly (text-to-speech) and Amazon Transcribe (speech-to-text).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What AWS service is used for personalized recommendations?

A

Amazon Personalize.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What AWS service provides a full machine learning platform?

A

Amazon SageMaker.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is Amazon Comprehend used for?

A

Natural Language Processing (NLP).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What insights can Amazon Comprehend extract from text?

A

Key phrases, places, people, brands, events, and sentiment analysis.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is custom classification in Amazon Comprehend?

A

A feature that allows users to define and train custom document categories.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is Named Entity Recognition (NER) in Amazon Comprehend?

A

A feature that extracts predefined entities like people, places, organizations, and dates.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is custom entity recognition in Amazon Comprehend?

A

A feature that allows training the model to identify specific terms, such as policy numbers. or phrases like escalation etc.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What does Amazon Transcribe do?

A

It converts speech into text using automatic speech recognition (ASR).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is ASR in Amazon Transcribe?

A

Automatic Speech Recognition – a deep learning technique to convert speech to text.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Can Amazon Transcribe remove sensitive data?

A

Yes, it supports automatic redaction of Personally Identifiable Information (PII).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How can you improve recognition of domain-specific words in Amazon Transcribe?

A

By using custom vocabularies.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

How are custom vocabularies different from custom language models?

A

Custom vocabularies focus on specific words; custom language models focus on context.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What feature does Amazon Transcribe offer to detect harmful speech?

A

Toxicity detection.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What data types does toxicity detection use?

A

Speech cues (tone and pitch) and text-based cues (like profanity or hate speech).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What are some categories of toxicity in Amazon Transcribe?

A

Sexual harassment, hate speech, threats, abuse, profanity, insult, graphic.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

How can you maximize transcription accuracy in Amazon Transcribe?

A

Use both custom vocabularies and custom language models.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What does Amazon Polly do?

A

It converts text into lifelike speech using deep learning.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What do lexicons in Amazon Polly do?

A

They allow custom pronunciation of specific words or acronyms (e.g., AWS as Amazon Web Services).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

What is SSML in Amazon Polly?

A

Speech Synthesis Markup Language – it controls pronunciation, pauses, emphasis, and tone.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
What can SSML be used for in Polly?
Adding breaks, whispering, emphasizing words, and controlling pronunciation.
26
What are the different voice engines in Amazon Polly?
Neural, standard, long-form, and generative.
27
Which Amazon Polly voice engine provides the most human-like speech?
Generative.
28
What are speech marks in Amazon Polly?
They indicate the timing of words in speech for applications like lip-syncing or word highlighting.
29
What is Amazon Rekognition?
Amazon Rekognition is a service that uses machine learning to find objects, people, texts, or scenes in images and videos.
30
How does Rekognition support content moderation?
It automatically detects inappropriate, unwanted, or offensive content, reducing the need for manual review to just 1 to 5% of content.
31
What additional service is used for human review in conjunction with Rekognition's content moderation?
Amazon Augmented AI (A2I) is used for human review when Rekognition flags content for further assessment.
32
What are Custom Labels in Amazon Rekognition?
Custom Labels allow you to train Rekognition to identify your own specific products, logos, or objects using your labeled training images.
33
What is Amazon Lex?
Amazon Lex is a service that allows you to build chatbots quickly using voice or text interfaces.
34
How does Amazon Lex integrate with other AWS services?
It integrates with AWS Lambda, Amazon Connect, Comprehend, and Kendra to perform actions based on user intents.
35
What is an intent in Amazon Lex?
An intent represents what the user wants to do (e.g., booking a hotel) and triggers the corresponding Lambda function to perform that action.
36
What are slots in Amazon Lex?
Slots are input parameters that the chatbot gathers from the user (e.g., city, check-in date) to fulfill an intent.
37
How does Amazon Lex use AWS Lambda?
When all required slot values are gathered, Lex invokes an AWS Lambda function to perform the backend operation, such as making a booking.
38
What happens after the Lambda function completes an action in Amazon Lex?
After execution, Amazon Lex responds to the user with confirmation or the outcome of the operation (e.g., 'Thank you, your reservation went through successfully').
39
What is Amazon Personalize?
Amazon Personalize is a fully managed machine learning service to build real-time personalized recommendations for users.
40
What are common use cases for Amazon Personalize?
Use cases include personalized product recommendations, re-ranking items, and customized direct marketing.
41
What is a 'recipe' in Amazon Personalize?
A recipe is a pre-built algorithm designed for specific recommendation use cases.
42
Can Amazon Personalize be used for forecasting?
No, Amazon Personalize is only used for personalized recommendations.
43
What are the different types of recipes available in Amazon Personalize?
1. User-Personalization-v2 (USER_PERSONALIZATION): Recommend items for users 2. Personalized-Ranking-v2: Rank a list of items for a user 3. Trending-Now: Recommend currently trending items 4. Popularity-Count: Recommend popular items 5. RELATED_ITEMS: Recommend similar items 6. Next Best Action: Suggest the next best user action 7. Item-Affinity: Extract user segments based on item preferences
44
What is Amazon Textract and what does it do?
Amazon Textract is a machine learning service that automatically extracts text, handwriting, forms, and tables from scanned documents like PDFs and images.
45
What is Amazon Kendra?
Amazon Kendra is a fully-managed, machine learning-powered document search service that allows natural language search across various document formats.
46
What types of documents can Amazon Kendra search through?
Kendra can extract answers from PDFs, Word documents, HTML, PowerPoint files, FAQs, and plain text.
47
What kind of search capability does Amazon Kendra provide?
Natural language search, similar to how users search on Google.
48
Can Amazon Kendra be fine-tuned? If yes, how?
Yes, search results can be fine-tuned using data importance, freshness, and custom filters.
49
What is Amazon Mechanical Turk and how is it used in AI?
Amazon Mechanical Turk is a crowdsourcing marketplace that provides a distributed virtual workforce(actual humans) to perform simple human tasks like image labeling, data collection, and business processing. It's especially useful in AI for tasks such as labeling datasets and reviewing recommendations, and it integrates with services like Amazon A2I and SageMaker Ground Truth.
50
What is Amazon Augmented AI (A2I)?
A2I is a service that enables human review of machine learning predictions to ensure accuracy and compliance.
51
When is human review triggered in Amazon A2I?
Human review is triggered when the ML model returns a low-confidence prediction.
52
What happens if a prediction is high-confidence in Amazon A2I?
The prediction is returned immediately to the client application without human review.
53
Who can perform the human review in Amazon A2I?
Human reviewers can be your employees, AWS Mechanical Turk workers, or pre-screened third-party vendors.
54
How does Amazon A2I help improve ML models?
Human-reviewed predictions are stored and can be fed back into the ML model to improve future performance.
55
What AWS services integrate with Amazon A2I?
A2I integrates with AWS AI services like Amazon Rekognition, Textract, and custom models built on SageMaker.
56
What is the benefit of using A2I in production environments?
It provides human oversight for critical ML predictions, ensuring better reliability and accuracy.
57
How does A2I support confidentiality?
It allows the use of pre-screened vendors and supports data security for sensitive information during human review.
58
What is Amazon Transcribe Medical?
A version of Amazon Transcribe designed to convert medical speech into text, supporting medical terminology and HIPAA compliance.
59
What is Amazon Comprehend Medical?
A natural language processing service designed to extract useful medical information from unstructured text.
60
What kind of text can Amazon Comprehend Medical analyze?
Physician’s notes, discharge summaries, test results, and case notes.
61
What does Amazon Comprehend Medical detect to ensure privacy?
Protected Health Information (PHI).
62
How can Transcribe Medical and Comprehend Medical be combined?
Audio is transcribed using Transcribe Medical, and the resulting text is analyzed by Comprehend Medical to extract structured medical insights.
63
What medical details can Comprehend Medical extract from text?
Age, profession, medication name, dosage, frequency, conditions, and procedures.
64
What is AWS Trainium chips used for?
AWS Trainium is ML chips build to perform deep learning on models having more than 100 billion parameters
65
What is AWS Inferentia chips used for?
Its ML chips build to deliver Inference at high performance and low cost
66
What are the benefits of using Trainium and Inferentia instances?
High performance, cost efficiency, and lowest environmental footprint
67
Which EC2 instance types are powered by AWS Inferentia and Trainium?
For Inferentia its Inf1 and Inf2 type instances. and for Trainium its Trn1 type instance.

AWS AI Practitioner Exam (7 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions