Other

Question 1

Amazon Comprehend

Answer 1

Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to uncover insights and relationships in text. It is specifically designed for tasks such as sentiment analysis, entity recognition, key phrase extraction, and language detection.

Question 2

Amazon Kendra

Answer 2

Machine learning tool that searches websites and applications to help users search content

Question 3

Llama

Answer 3

a series of large language models trained on publicly available data, and built on the transformer architecture. It can generate coherent and contextually appropriate text.

Question 4

Jurassic

Answer 4

Family of models from AI21 Labs supported use cases such as question answering, summarization, draft generation, advanced information extraction, and ideation for tasks requiring intricate reasoning and logic.

Question 5

Claude

Answer 5

Anthropic’s frontier, state-of-the-art large language model that offers important features for enterprises like advanced reasoning, vision analysis, code generation, and multilingual processing.

Question 6

AWS Trainium

Answer 6

2nd generation machine learning (ML) accelerator for deep learning training. Used by Amazon Elastic Compute Cloud (EC2)

Question 7

AWS Inferentia

Answer 7

accelerators designed to deliver high performance at the lowest cost in Amazon EC2 for your deep learning (DL) and generative AI inference applications.

Question 8

Amazon SageMaker GroundTruth Plus

Answer 8

provides a fully managed data labeling service that helps deliver high-quality annotations. It uses a combination of human labelers and machine learning

Question 9

multi-class vs. multi-label classification

Answer 9

Multi-class classification assigns each instance to one of several possible classes

Multi-label classification assigns each instance to one or more classes

Question 10

Amazon Stagemaker studio

Answer 10

Offers a broad set of fully managed integrated development environments (IDEs) for ML development, including JupyterLab, Code Editor based on Code-OSS (Visual Studio Code – Open Source), and RStudio.

Question 11

Amazon Sagemaker -
Asynchronous Inference, Batch transformation & real-time

Answer 11

Asynchronous Inference is used for requests with large payload sizes up to 1GB, long processing times, and near real-time latency requirements.

Batch transform - used to get predictions for an entire dataset

Real-time - For persistent, real-time endpoints that make one prediction at a time

Question 12

Are large language models deterministic or discriminative?

Answer 12

Large Language Models (LLMs) are non-deterministic, which implies that the generated text may be different for every user that uses the same prompt