classification

Definition

Assigning an input to one of a fixed, predefined set of categories — spam or not, which of a thousand object classes, which sentiment. Its long dominance comes from how cleanly it evaluates: compare the predicted label to the true one and accuracy falls out. Contrast regression, where the output is continuous, and generation, where the output space is open-ended and scoring is much harder.

Explainers using this term

• Graph Neural Networks from Scratch — Learning from ConnectionsSemi-Supervised Classification with Graph Convolutional Networks
• Activation Functions from Scratch — Why Nonlinearity Is Non-NegotiableDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification