> Glossary

AI and machine learning terms explained in plain language.

A

Attention

A mechanism that allows a model to focus on relevant parts of the input when producing output. Self-attention computes relationships between all positions in a sequence.

B

Backpropagation

An algorithm for computing gradients of the loss function with respect to model weights, used to update parameters during training.

C

CNN

Convolutional Neural Network — a type of neural network designed for processing grid-like data such as images, using convolutional layers to detect spatial patterns.

E

Embedding

A learned dense vector representation of discrete data (words, tokens, items) in a continuous vector space where similar items are nearby.

F

Fine-Tuning

The process of taking a pre-trained model and further training it on a specific dataset to adapt it for a particular task or domain.

G

Gradient Descent

An optimization algorithm that iteratively adjusts model parameters in the direction that reduces the loss function.

H

Hallucination

When an AI model generates plausible-sounding but factually incorrect or nonsensical information.

Related:LLMRAG

L

LLM

Large Language Model — a neural network trained on vast amounts of text data that can generate, understand, and reason about natural language.

N

Neural Network

A computing system inspired by biological neural networks, consisting of interconnected layers of nodes (neurons) that learn to map inputs to outputs.

P

Prompt Engineering

The practice of designing and optimizing input prompts to effectively guide AI models toward desired outputs.

R

RAG

Retrieval-Augmented Generation — a technique that enhances LLM responses by first retrieving relevant documents from an external knowledge base, then using them as context for generation.

RNN

Recurrent Neural Network — a type of neural network designed for sequential data, where the output from previous steps feeds into the current step.

T

Token

The basic unit of text that language models process. A token can be a word, subword, or character depending on the tokenization method.

Related:LLMEmbedding

Transformer

A neural network architecture based on self-attention mechanisms, introduced in 'Attention Is All You Need' (2017). The foundation of modern LLMs like GPT and BERT.

V

Vector Database

A database optimized for storing and searching high-dimensional vectors (embeddings), enabling fast similarity search for applications like RAG.

Related:EmbeddingRAG