machine learning
The branch of AI in which a program learns patterns from example data instead of following rules a person wrote.
In more detail
A training process adjusts a model's parameters until its predictions fit the examples, and the trained model then makes predictions on new input. Large language models are machine learning models trained on huge amounts of text. Google's Rules of Machine Learning advise starting with simple heuristics and adding a model only when it beats them.
Related terms
- artificial intelligence — Computer systems that perform tasks normally needing human intelligence, such as understanding language, recognising images or making predictions.
- model training — The process that sets a model's weights by adjusting them, over many examples, until its predictions fit the data.
Taught in
- What An AI Engineer Does — AI Engineering: LLM Apps, RAG & Agents