Reference library

AI Glossary

Plain-English explanations for AI and machine-learning terms, written for professionals using AI in real work.

82 terms across 5 categories.

Browse by category

Fundamentals
Techniques
Tools & Models
Applications
Ethics & Safety

Start here

01
Artificial Intelligence (AI)
Artificial intelligence is the broad field of computer science focused on creating systems that can perform tasks typically requiring human intelligence. These tasks include understanding language, recognising images, making decisions, and learning from experience.
Fundamentals
02
Large Language Model (LLM)
A large language model is an AI system trained on vast quantities of text data that can understand, generate, and reason about human language. LLMs use the transformer architecture and contain billions of parameters, enabling them to perform a wide range of language tasks.
Tools & Models
03
Machine Learning (ML)
Machine learning is a subset of AI where systems learn from data and improve their performance over time without being explicitly programmed for every scenario. Instead of following hard-coded rules, ML models identify patterns in data and use them to make predictions or decisions.
Fundamentals
04
Prompt Engineering
Prompt engineering is the practice of crafting and refining the instructions (prompts) given to an AI model to get the best possible output. It involves techniques like providing context, examples, and constraints to guide the model's response.
Tools & Models

Showing 82 of 82 terms

ABC D E F G H IJK L M N O P Q R S T U VWXYZ

A

C

D

E

F

G

H

HallucinationIn AI, a hallucination occurs when a model generates information that sounds plausible but is factually incorrect or ent…Ethics & Safety

I

K

Knowledge GraphA knowledge graph is a structured representation of entities and their relationships, stored as connected nodes and edge…Techniques

L

M

N

O

OverfittingOverfitting occurs when a machine learning model learns the training data too well — including its noise and outliers — …Fundamentals

P

Q

QuantizationQuantization is a model optimisation technique that reduces numerical precision of weights and activations, such as from…Techniques

R

S

T

U

V

Z

Zero-Shot LearningZero-shot learning is when a model performs a task it was not explicitly trained on by leveraging general knowledge lear…Techniques

Want guided practice after reading?

Our programme follows a structured Level 4 curriculum with project-based learning, practical workflows, and guided implementation across business and career use cases. Funded route available for UK citizens and ILR holders.

Check If You Qualify See Pricing Options