Core concepts
Machine Learning
A type of AI where systems learn patterns from data rather than being explicitly programmed with rules.
01 ——
In plain English
Machine Learning (ML) is the field of AI focused on systems that improve from experience. Instead of writing rules ("if email contains 'win a prize', mark as spam"), you give the system many labelled examples and let it figure out the pattern itself.
Three main types:
- Supervised learning — train on labelled data (this email is spam, this isn't)
- Unsupervised learning — find structure in unlabelled data (cluster customers)
- Reinforcement learning — learn from trial, error, and rewards (game-playing AI)
Where it's used: Recommendation engines (Netflix, Spotify), fraud detection, ad targeting, demand forecasting, medical imaging, and the underlying training of every LLM and diffusion model.
ML vs deep learning vs AI:
- AI = the broad field
- ML = a subset of AI that learns from data
- Deep learning = a subset of ML that uses neural networks
02 ——
Related terms
AI
Artificial Intelligence — software that performs tasks normally requiring human intelligence, like understanding language, recognising images, or generating content.
Deep Learning
A type of machine learning that uses layered neural networks to learn complex patterns — the foundation of modern AI.
Neural Network
A computing system inspired by the brain, made up of layers of connected "neurons" that learn patterns from data — the building block of modern AI.
Training Data
The dataset an AI model learns from — its quality, diversity, and biases directly shape what the model can do and how well it does it.
Fine-tuning
Further training a pre-trained AI model on your own data to specialise it for a specific task or style.
Back to glossaryLast reviewed May 2026