AWS AI Practitioner Practice Test 1 Flashcards
Retrieval Augmented Generation (RAG)
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.
Transformer Models
Transformer models use a self-attention mechanism and implement contextual embeddings to handle sequential data; such as language; in an efficient and scalable way.
Amazon Bedrock and Amazon SageMaker JumpStart
Amazon Bedrock and Amazon SageMaker JumpStart are recommended AWS services for developing Large Language Model (LLM) based solutions.
Model Customization in Amazon Bedrock
Continued pre-training uses unlabeled data to pre-train a model; whereas; fine-tuning uses labeled data to train a model.
Labeled and Unlabeled Data
Labeled data is annotated with output labels and is used for supervised learning; whereas; unlabeled data lacks annotations and is used for unsupervised learning.
Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs)
Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) are used in Amazon Q Business web application workflow.
Knowledge Bases for Amazon Bedrock
OpenSearch Serverless vector store is the default vector database supported by Knowledge Bases for Amazon Bedrock.
Amazon Bedrock
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.
Amazon SageMaker Ground Truth
Amazon SageMaker Ground Truth helps build high-quality training datasets for machine learning models.
Inference Parameters in Amazon Bedrock
Use higher Temperature to get more creative responses for the same prompt on Amazon Bedrock.
Amazon Q Developer
Amazon Q Developer is powered by Amazon Bedrock.
Foundation Models (FMs) and Large Language Models (LLMs)
Foundation Models serve as a broad base for various AI applications by providing generalized capabilities
Amazon SageMaker Clarify
Amazon SageMaker Clarify helps understand how an input feature contributes to the predictions of a machine learning model.
AWS Global Infrastructure
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.
Supervised Learning
Linear regression and neural network are examples of supervised learning.
Amazon Bedrock
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.
Negative Prompting
Negative prompting refers to guiding a generative AI model to avoid certain outputs or behaviors when generating content.
Amazon Q in QuickSight
With Amazon Q in QuickSight; customers get a generative BI assistant that allows business analysts to use natural language to build BI dashboards.
Amazon SageMaker Model Dashboard
Amazon SageMaker Model Dashboard aggregates and displays data from Amazon SageMaker Model Cards; SageMaker Model Monitor and SageMaker Endpoint services.
Top K
Top K represents the number of most likely candidates that the model considers for the next token.
Reinforcement Learning
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.
