Textbook of AI

Also known as: ML, statistical learning

Machine Learning (ML) is the subset of AI concerned with algorithms that improve their performance at a task through experience—that is, through exposure to data. Rather than writing explicit rules, the programmer provides examples and lets the system discover the patterns for itself. Tom Mitchell's classical definition states that a program learns from experience E with respect to task T and performance measure P, if its performance on T, as measured by P, improves with E.

The three classical paradigms of ML are supervised learning (learning from input–output pairs), unsupervised learning (finding structure in unlabelled data), and reinforcement learning (learning through interaction and reward). A fourth paradigm, self-supervised learning, has risen to prominence with language models, where the model generates its own supervisory signal from the structure of the data.

The central challenge of machine learning is generalisation: performing well on data the model has never seen. A model that perfectly memorises its training set but fails on new examples is said to be overfitting. The art of ML lies in balancing capacity and regularisation, so that a model captures genuine patterns without fitting noise. ML now powers most of modern AI, from web search and recommendation to autonomous vehicles and scientific discovery.