AI Glossary
38 terms defined
A
Artificial General Intelligence
Artificial General Intelligence (AGI), also referred to as **General AI** or **True AI**, is a theoretical form of artificial intelligence that possesses...
AI Agent
An AI Agent, short for Artificial Intelligence Agent, is an autonomous system designed to perform tasks that typically require human intelligence. It...
Alignment
Alignment**, in the context of AI research, refers to the process of ensuring that artificial intelligence systems operate in ways that align with human...
Attention Mechanism
An **Attention Mechanism** is a technique used in neural networks to enable models to focus on specific parts of input data during processing. This...
C
Chain-of-Thought
Chain-of-Thought (CoT): A Comprehensive Overview summary: Chain-of-Thought (CoT): A Comprehensive Overview
Computer Vision
Computer Vision (CV) is a field of artificial intelligence (AI) that enables computers and systems to derive meaningful information from digital images,...
Context Window
Window refers to the maximum amount of text an Large Language Model (LLM) can process at any given time. It is also known as context length or...
E
Embedding
An embedding is a type of numerical representation that captures semantic meaning in a compact form. It converts high-dimensional data—such as words,...
Epoch
An **epoch** refers to one complete pass through the entire training dataset in machine learning. During an epoch, every sample in the dataset is...
Explainability
Explainability, or Explainable AI (XAI), refers to the ability of machine learning models to provide clear, interpretable insights into their...
F
Few-Shot Learning
Few-Shot Learning is a machine learning technique where models are trained or fine-tuned using only a small number of examples for a specific task. This...
Fine-tuning
Fine-tuning is the process of further training a pre-trained model on a specific dataset to enhance its performance on a particular task. It involves...
G
Generative Adversarial Network
A Generative Adversarial Network (GAN) is a type of artificial intelligence model used in unsupervised learning. It consists of two neural networks—a...
GPU
A Graphics Processing Unit (GPU), also known as a graphics card or video chip, is a specialized electronic circuit designed to handle the rendering of...
H
H100
The H100, or NVIDIA Hopper H100 GPU, is the latest flagship architecture from NVIDIA designed specifically for handling massive AI workloads. Part of the...
Hallucination
Hallucination, in the context of AI and machine learning, refers to a phenomenon where an artificial intelligence model generates incorrect or nonsensical...
L
Latency
Latency** refers to the time delay that occurs between a request being made to an AI model and the system generating a response. It is a critical metric...
Large Language Model
A **Large Language Model (LLM)** is a type of artificial intelligence algorithm that leverages deep learning techniques to process and understand human...
M
Machine Learning
Machine Learning (ML) is a subset of Artificial Intelligence (AI) that focuses on the development of algorithms capable of learning patterns from data...
Multi-Agent System
A Multi-Agent System (MAS) is a computational framework composed of multiple intelligent agents that interact and collaborate to achieve common goals or...
N
Neural Network
A **Neural Network** (often abbreviated as NN) is a computational model inspired by the structure and function of biological neural networks in the human...
Natural Language Processing
Natural Language Processing (NLP) is an interdisciplinary field that combines linguistics, computer science, and machine learning to enable machines to...
P
Parameter
A **parameter** in machine learning refers to an internal variable within a model that is learned during the training process. These parameters are...
Pre-training
Pre-training refers to the initial phase of training a machine learning model on a large, diverse dataset to learn general patterns and representations...
Prompt Engineering
Prompt Engineering (PE)** is the art and science of crafting precise, structured, and strategically designed text inputs that guide generative AI models...
R
Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG)** is a cutting-edge AI framework that enhances large language models (LLMs) by incorporating external knowledge...
Reinforcement Learning
Reinforcement Learning (RL), a subfield of machine learning, focuses on training intelligent agents to make sequential decisions in dynamic environments....
Reinforcement Learning from Human Feedback
Reinforcement Learning from Human Feedback (RLHF) is a technique that aligns AI models with human values by utilizing human feedback as a reward signal....
T
Tokenization
Learn what Tokenization means in AI and machine learning. Comprehensive definition, examples, and FAQ.
Tool Use
Tool Use refers to the ability of an AI model, particularly large language models (LLMs), to utilize external tools such as calculators, search engines,...
TPU
The Tensor Processing Unit (TPU) is an AI accelerator, specifically designed as an application-specific integrated circuit (ASIC) developed by Google. It...
Transformer
The Transformer is a deep learning architecture introduced in 2017 by Google researchers Ashish Vaswani, Noam Shazeer, and others in their seminal paper...