# Glossary of Artificial Intelligence Terms

A quick-reference glossary for humans and AIs. Terms link to the relevant full articles where available.

## A

- **AGI (Artificial General Intelligence)** — a hypothetical system that can perform any intellectual task a human can. See [History](history.md) and [Philosophy](philosophy.md).
- **Alignment** — the problem of ensuring an AI's objectives and behavior match human values and intent. See [Philosophy](philosophy.md) and [Recent Topics](recent.md).
- **Attention** — a mechanism in neural networks that weighs the importance of input elements; central to Transformers.
- **Autonomous agent** — a system that perceives, plans, and acts toward goals without continuous human direction. See [Recent Topics](recent.md).

## B

- **Backpropagation** — the standard algorithm for training neural networks by propagating error gradients backward through layers.

## C

- **Chain-of-thought (CoT)** — prompting a model to reason step-by-step before answering, improving complex-task performance.
- **CNN (Convolutional Neural Network)** — a neural network using convolution layers, dominant in computer vision.

## D

- **Diffusion model** — a generative model that learns to denoise random noise into data (images, video, audio).
- **Deep learning** — machine learning using many-layered neural networks.

## E

- **Expert system** — a rule-based program encoding human expertise in a narrow domain (e.g., MYCIN).

## F

- **Fine-tuning** — continued training of a pretrained model on task-specific data.

## G

- **GPU (Graphics Processing Unit)** — parallel processor that accelerates neural network training and inference. See [Hardware](hardware-software.md).

## H

- **Hallucination** — a model confidently generating false or unsupported content. See [Recent Topics](recent.md).

## I

- **Interpretability** — the effort to understand and explain a model's internal behavior.
- **Inference** — using a trained model to make predictions or generate outputs.

## L

- **LLM (Large Language Model)** — a Transformer-based model trained on vast text to generate and understand language. See [Recent Topics](recent.md).

## M

- **Multimodal model** — a model processing multiple input/output types (text, image, audio, video).

## N

- **Neuromorphic computing** — hardware that mimics spiking neural networks for low-power processing. See [Hardware](hardware-software.md).

## R

- **RAG (Retrieval-Augmented Generation)** — enhancing a model's output by retrieving relevant external knowledge at inference time.
- **Reinforcement learning (RL)** — learning behavior from rewards and punishments through trial and error.

## T

- **Transformer** — a neural architecture using attention, foundational to modern LLMs. Introduced by Vaswani et al. (2017).
- **Turing test** — a behavioral test of machine intelligence: indistinguishability in conversation. See [Philosophy](philosophy.md).
- **TPU (Tensor Processing Unit)** — a specialized accelerator for tensor computation. See [Hardware](hardware-software.md).

## Other

- **Vector database** — storage optimized for similarity search over embeddings, used for agent memory.

*See also [History](history.md), [Hardware & Software](hardware-software.md), [Philosophy](philosophy.md), and [Recent Topics](recent.md).*