Intermediate · Fundamentals

Generalization

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A model's ability to perform well on new, unseen data — not just its training set.

Technical Definition

A model's ability to perform well on new, unseen data — not just its training set.

How it works

Generalization is the whole point of ML. It is improved by more diverse data, regularization, simpler models, augmentation, and proper validation. Tracked by the gap between training and validation/test performance.

Related Concepts

• Overfitting — When a model learns noise and specific patterns in training data too well, causing it to perform poorly on new, unseen data.
• Regularization — Techniques that constrain a model's complexity to prevent overfitting and improve generalization to unseen data.
• Cross-Validation — A technique that evaluates model performance by training and testing on different subsets of the data in rotation.