Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

my deck > AI/ML > Flashcards

AI/ML Flashcards

1
Q

What is the purpose of SageMaker Ground Truth Plus?

A

Helps customers create high-quality training data sets

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

Does SageMaker Ground Truth require manual labeling?

A

No, there is no need to build labeling applications and manage labeling workforces

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

How does SageMaker Ground Truth handle SLA?

A

Provides mutually agreed-upon upfront SLA for label quality

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

How does SageMaker Ground Truth handle feedback?

A

Provides a feedback option on labels through a review interface

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

What is the purpose of SageMaker Inference Recommender?

A

it helps you choose the best available compute instance and configuration to deploy machine learning models for optimal inference performance and cost. It automatically selects the right compute instance type, instance count, container parameters, and model optimizations for inference to maximize performance and minimize cost.

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

What are the benefits of SageMaker Inference Recommender?

A
  • It automates load testing and optimizes model performance across ML instances
  • It reduces the time it takes to get ML models from dev to prod in a cost-effective way
  • Provides recommendations for best price performant instance type and endpoint configuration for model deployment
  • Free to use, customer only pays for instance usage during testing
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is SageMaker Training Compiler?

A

It is a capability of SageMaker that makes these hard-to-implement optimizations to reduce training time on GPU instances. The compiler optimizes DL models to accelerate training by more efficiently using SageMaker machine learning (ML) GPU instances.

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

What are the key takeaways of SageMaker Training Compiler?

A
  • It’s for training, not inferencing
  • Deep learning Container, but at this time tested again Hugging Face NLP models
  • PyTorch or TensorFlow
  • minimal code changes
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is Amazon Polly?

A

API-driven service that converts text into lifelike speech

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

What are the key takeaways for Amazon Polly?

A
  • Offers 60+ lifelike (with 20+ NTTS) voices across 31 languages
  • Offers neutral, newscaster, and conversational styles with NTTS
  • Developers can store, replay and distribute generated speech
  • Organizations with specific needs can build their Brand Voice with Polly
  • No prior machine learning experience required!
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is Amazon Translate?

A

A text translation service that uses advanced machine learning technologies to provide high-quality translation on demand.

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

How can you use Amazon Translate?

A

To translate unstructured text documents or to build applications that work in multiple languages

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

What are the key takeaways for Amazon Translate?

A
  • Broad language coverage
  • low latency (<150ms/sentence, <80ms/convo)
  • data security
  • broad regional (17) coverage
  • Customizable translation
  • Document batch translation
  • Broad domain (11) coverage
  • Pay per use
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is Amazon Transcribe?

A

A fully-managed and continuously trained automatic speech recognition (ASR) service

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

What are the key takeaways for Amazon Transcribe?

A
  • highly accurate, efficient, and scalable
  • easy to use speech-to-text capabilities and APIs to build voice-enabled applications
  • no prior ML experience required
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is Amazon Comprehend?

A

A natural-language processing (NLP) service that uses machine learning to uncover valuable insights and connections in text

17
Q

What are the key takeaways for Amazon Comprehend?

A
  • Intelligent doc processing
  • Automation of email workflows
  • customer support tickets routing
  • document and media tagging
  • Customer sentiment analysis
  • contact center call analysis
  • PII detection and redaction
18
Q

What is Lex Automated Chatbot Designer?

A

It extends Amazon Lex by analyzing thousands of lines of transcripts in a couple of hours to give you an automated initial bot design that includes common intents

19
Q

What is Amazon Textract AnalyzeID

A

An API for Amazon Textract that will automatically extract relevant info from IDs without the need for templates or configuration

20
Q

What are the key takeaways for Amazon Personalize?

A
  • New recommenders optimized for retail and media & entertainment use cases
  • New recipe type called USER_SEGMENTATION which includes two new recipes, aws-item-affinity and aws-item-attribute, both of which can be used to identify users based on their preferences
21
Q

What is Kendra Experience Builder?

A

Deploys a fully functional and customizable search experience in a few clicks, without any coding or ML experience. Use an intuitive, visual workflow to build, customize, and launch a Kendra-powered search application

22
Q

What is Kendra Search Analytics Dashboard?

A

Allows you to view quality and usability metrics associated with a Kendra-powered search app

23
Q

What is Kendra Custom Document Enrichment?

A

Builds a custom ingestion pipeline that can pre-process docs before they get indexed into Kendra

24
Q

What are the benefits of using Amazon Lex automated chatbot designer?

A
  • Reduced manual effort
  • Accelerate conversation design
  • improved customer experience
25
Q

What is the purpose of Speech Synthesis Markup Language (SSML) in Amazon Polly?

A

SSML is used to markup input files for added control such as speech rate, pitch, and more.

26
Q

Can Amazon Comprehend be used for real-time analysis?

A

Yes

  • Can directly provide up to 5,000 bytes of text in the Console and get insights in real-time
  • Provides synchronous single-document processing and multi-document processing for up to 25 documents, 5000 bytes in size in real-time
27
Q

How many documents can Comprehend process using Batch processing?

A

For larger files, Batch Processing allows

asynchronous processing of up to 1,000,000 documents up to 5GB in size

28
Q

What inputs are needed from customers to run Inference Recommender?

A
  1. Inference Container Image as ECR URIs
  2. S3 location for Model Artifact and Sample Payload
  3. Model metadata registered in SageMaker Model Registry

my deck (14 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions