Machine LearningA conceptual sequence. These methods coexist; later ideas do not make earlier ones obsolete.
Knowledge book
Machine Learning
Overview
Learning patterns from evidence, then testing what generalizes.
A model that fits the training data is interesting. A model that survives new data is useful.
Data
Features
Model
Training
Prediction
Evaluation
Improvement
Published in this topic
01What does it actually mean for a machine to learn?
Start with the gap between memorizing examples and learning a pattern that survives new data.
These sections organize published articles and planned coverage. New articles can be added without changing the section order.