Glossary
Machine learning — Glossary
A family of methods that improve model performance by learning patterns from data instead of relying only on hand-coded rules.
Full definition
Machine learning (ML) trains models to make predictions or decisions by optimizing performance on examples. In supervised learning, models map inputs to labeled outputs. Unsupervised methods find structure without labels. Reinforcement learning optimizes sequential decisions using rewards.
ML systems generalize only to the extent that new data resembles the conditions of training and evaluation. Careful splits, metrics aligned to real costs, and monitoring after deployment are part of competent practice. Deep learning is a prominent subfield that uses multi-layer neural networks as the model class.