Foundations
Supervised Learning
Training a model on labeled examples, where each input comes paired with the correct answer.
In supervised learning you hand the model inputs alongside the right outputs, like photos tagged cat or dog, and it learns to map one to the other. It is the most common and best-understood style of machine learning, used for everything from spam detection to medical image classification. Its main cost is the labeled data itself, since someone or something has to produce all those correct answers first.
Reference: Wikipedia: Supervised Learning
Related terms
Unsupervised Learning
Training a model on data with no labels, so it has to find structure and patterns on its own.
Reinforcement Learning
Training a model through trial and error, rewarding good outcomes and penalizing bad ones until it learns a strategy.
Training Data
The examples a model learns from, whose size, quality, and bias largely determine how the model turns out.
Machine Learning
A way of building software that learns patterns from examples instead of being told exactly what to do.