Which companies are associated with Bedrock Foundation Models? AI21 labs, Cohere, Stability, Amazon, Meta, Mistral Google, IBM, Microsoft, OpenAI Intel, AMD, NVIDIA, Qualcomm Facebook, Apple, Netflix, Google

AI21 labs, Cohere, Stability, Amazon, Meta, Mistral

AWS AI Practitioner

Flashcard

Learn Mode

Match

Library

Create

Flashcards

Library

Match (Coming Soon)

Computer Science - Software Engineering

user_kambeorv Created by 7 mon ago

Cards in this deck(100)

What is used to generate new data that is similar to the data it was trained on?

What is the model or base technology used to train a large language model, such as GPT-4?

What type of AI is designed to generate coherent human-like text, such as GPT-4?

What term describes when the generated text may be different for every user that uses the same prompt?

What AWS service allows you to build Generative AI applications while keeping control of your own data?

Which companies are associated with Bedrock Foundation Models?

What type of models handle varied types of input and outputs?

What are high-performing foundation models from AWS that offer image, text, and multi-model choices?

What process involves adapting a copy of a foundational model with your own data by changing the weights?

What improves the performance of a pre-trained foundation model on domain-specific tasks using labeled examples?

What is the process of providing unlabeled data to continue the training of a foundation model, also known as adaptation fine-tuning?

What is part of instruction-based fine-tuning that includes system instructions for context and a messages array?

What is similar to single-turn messaging but involves multiple user/assistant interactions?

What are some aspects of fine-tuning a model, including cost and computational intensity?

What is the broader concept of re-using a pre-trained model to adapt it to a new related task?

What process evaluates a model for quality control using built-in tasks like text summarization and Q&A?

What is a curated collection of data designed specifically to evaluate the performance of language models?

What are some automated metrics used to evaluate foundation models?

What metric evaluates automatic summarization and machine translation systems by measuring matching n-grams?

What metric evaluates the quality of generated text, especially for translations, by looking at n-grams?

What metric measures semantic similarity between generated text by comparing contextual embeddings?

What metric evaluates how well a model predicts the next token, with lower values being better?

What does RAG stand for, and how does it allow a foundation model to reference external data?

What are the default AWS vector databases used for real-time similarity queries?

What AWS service is a search and analytics database that supports real-time similarity queries?

What type of database is Amazon DocumentDB, and what capabilities does it offer?

What type of database is Amazon Aurora, and what is its primary characteristic?

What type of database is Amazon RDS for PostgreSQL, and what is its primary characteristic?

What type of database is Amazon Neptune, and what is its primary use case?

What are some data sources for Bedrock RAG?

What is the process of converting raw text into a sequence of tokens?

What is the process of splitting text into individual words called?

What type of tokenization involves splitting some words into smaller units?

What term describes the number of tokens an LLM can consider when generating text?

What are vectors that capture many features for one input token, such as semantic meaning and sentiment?

What controls the interaction between users and Foundation Models by filtering content and removing PII?

What manages and carries out various multi-step tasks related to infrastructure provisioning and application deployment?

What is the integration that allows model invocation logging to be sent to CloudWatch and S3?

What are the pricing options for Bedrock, including on-demand and batch processing?

What are some model improvement techniques in cost order, including prompt engineering and fine-tuning?

What involves developing, designing, and optimizing prompts to enhance the output of Foundation Models?

What are the aspects of prompt engineering, including instructions and context?

What technique involves explicitly instructing the model on what not to include or do in its response?

What defines how the model should behave and reply?

What term describes the creativity of the model's output, ranging from 0 to 1?

What does Top P (0 - 1) refer to in the context of model output?

What limits the number of probable words considered by the model?

What defines the maximum length of an answer generated by the model?

What are tokens that signal the model to stop generating output?

What factors impact the prompt latency, or how fast the model responds?

What is the process of presenting a task to the model without providing examples or explicit training?

What involves providing examples of a task to the model to guide its output?

What involves dividing the task into a sequence of reasoning steps for more structure and coherence?

What simplifies and standardizes the process of generating prompts?

What is a fully managed Gen-AI assistant for employees based on a company's knowledge and data?

What connects to 40+ popular enterprise data sources like S3 and RDS?

What allows interaction with 3rd party services like Jira and ServiceNow?

What controls and customizes responses to organizational needs, similar to Bedrock guardrails?

What allows the creation of Gen-AI powered apps without coding using natural language?

What answers questions about AWS documentation and service location, integrating with IDEs like VS Code?

What visualizes data and creates dashboards, understanding natural language questions?

What provides guidance and suggestions for EC2 instance types best suited to new workloads?

What is a way to deploy a chatbot that knows about your AWS account, accessible from ChatBot?

What is an ETL service used to move data, with Q helping to answer questions and troubleshoot?

What is a GenAI app-building playground powered by Bedrock?

What are the components of AI, including data layer and application layer?

What is a type of AI for building methods that allow machines to learn?

What uses neurons and synapses to train a model, processing complex patterns in data?

What are the components of a neural network architecture?

What model processes a sentence as a whole instead of word by word, being faster and more efficient?

What are some machine learning terms, including GPT, BERT, and RNN?

What type of data includes both input features and corresponding output labels?

What type of data includes only input features without any output labels?

What type of data is organized in a structured format, often in rows and columns?

What type of data is arranged in a table with rows representing records and columns representing features?

What type of data consists of data points collected or recorded at successive points in time?

What type of data doesn't follow a specific structure and is often text-heavy or multimedia content?

What type of unstructured data includes text such as articles, social media posts, or customer reviews?

What type of data is in the form of images, which can vary widely in format and content?

What type of learning involves predicting the output for new unseen input data using labeled data?

What type of supervised learning is used to predict numeric values based on input data?

What type of supervised learning is used to predict the categorical label of input data?

What is the dataset used to train the model, usually comprising 60-80% of the total dataset?

What is the dataset used to tune model parameters and validate performance, usually around 10-20% of the total dataset?

What is the dataset used to evaluate the final model performance, typically 10-20% of the total dataset?

What is the process of using domain knowledge to select and transform raw data into meaningful features?

What are some feature engineering techniques, including extraction and transformation?

What type of learning aims to discover inherent patterns, structures, or relationships within input data?

What unsupervised learning technique is used to group similar data points into clusters?

What technique identifies associations between inputs in unsupervised learning?

What technique identifies data that deviates significantly from typical behavior in unsupervised learning?

What type of learning uses a small amount of labeled data and a large amount of unlabeled data to train systems?

What type of learning involves a model generating pseudo-labels for its own data without human labeling?

What type of ML involves an agent learning to make decisions by performing actions to maximize rewards?

What are some key concepts of reinforcement learning, including agent and environment?

What is the process of reinforcement learning, including observing the environment and updating policy?

What involves using human feedback to help ML models self-learn more efficiently?

What is the process of RLHF, including data collection and optimizing the language model?

What occurs when a model performs well on training data but poorly on evaluation data?

What occurs when a model performs poorly on training data?

Ask Our AI Tutor

Get Instant Help with Your Questions

Need help understanding a concept or solving a problem? Type your question below, and our AI tutor will provide a personalized answer in real-time!

How it works

Ask any academic question, and our AI tutor will respond instantly with explanations, solutions, or examples.

Get Started

Browse questions and discover topic-based flashcards
Practice with engaging flashcards designed for each subject
Strengthen memory with concise, effective learning tools

Discover By Topic

AWS AI Practitioner

Related Decks