AWS AI Practitioner Practice Test 1

Question 1

Retrieval Augmented Generation (RAG)

Answer 1

With Knowledge Bases for Amazon Bedrock; you can give FMs and agents contextual information from your company’s private data sources for RAG to deliver more relevant; accurate; and customized responses.

Question 2

Transformer Models

Answer 2

Transformer models use a self-attention mechanism and implement contextual embeddings to handle sequential data; such as language; in an efficient and scalable way.

Question 3

Amazon Bedrock and Amazon SageMaker JumpStart

Answer 3

Amazon Bedrock and Amazon SageMaker JumpStart are recommended AWS services for developing Large Language Model (LLM) based solutions.

Question 4

Model Customization in Amazon Bedrock

Answer 4

Continued pre-training uses unlabeled data to pre-train a model; whereas; fine-tuning uses labeled data to train a model.

Question 5

Labeled and Unlabeled Data

Answer 5

Labeled data is annotated with output labels and is used for supervised learning; whereas; unlabeled data lacks annotations and is used for unsupervised learning.

Question 6

Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs)

Answer 6

Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) are used in Amazon Q Business web application workflow.

Question 7

Knowledge Bases for Amazon Bedrock

Answer 7

OpenSearch Serverless vector store is the default vector database supported by Knowledge Bases for Amazon Bedrock.

Question 8

Amazon Bedrock

Answer 8

Amazon Bedrock is a fully managed service that offers a choice of high-performing FMs and the ability to privately customize the FMs with your data.

Question 9

Amazon SageMaker Ground Truth

Answer 9

Amazon SageMaker Ground Truth helps build high-quality training datasets for machine learning models.

Question 10

Inference Parameters in Amazon Bedrock

Answer 10

Use higher Temperature to get more creative responses for the same prompt on Amazon Bedrock.

Question 11

Amazon Q Developer

Answer 11

Amazon Q Developer is powered by Amazon Bedrock.

Question 12

Foundation Models (FMs) and Large Language Models (LLMs)

Answer 12

Foundation Models serve as a broad base for various AI applications by providing generalized capabilities

Question 13

Amazon SageMaker Clarify

Answer 13

Amazon SageMaker Clarify helps understand how an input feature contributes to the predictions of a machine learning model.

Question 14

AWS Global Infrastructure

Answer 14

Each AWS Region consists of a minimum of three Availability Zones (AZ); and each Availability Zone (AZ) consists of one or more discrete data centers.

Question 15

Supervised Learning

Answer 15

Linear regression and neural network are examples of supervised learning.

Question 16

Amazon Bedrock

Answer 16

Leverage Amazon Bedrock to make a separate copy of the base FM model and train this private copy of the model using the labeled training dataset.

Question 17

Negative Prompting

Answer 17

Negative prompting refers to guiding a generative AI model to avoid certain outputs or behaviors when generating content.

Question 18

Amazon Q in QuickSight

Answer 18

With Amazon Q in QuickSight; customers get a generative BI assistant that allows business analysts to use natural language to build BI dashboards.

Question 19

Amazon SageMaker Model Dashboard

Answer 19

Amazon SageMaker Model Dashboard aggregates and displays data from Amazon SageMaker Model Cards; SageMaker Model Monitor and SageMaker Endpoint services.

Question 20

Top K

Answer 20

Top K represents the number of most likely candidates that the model considers for the next token.

Question 21

Reinforcement Learning

Answer 21

Reinforcement learning involves an agent interacting with an environment by taking actions and receiving rewards or penalties; learning a policy to maximize cumulative rewards over time.