Skip to content

training

Softmax

An activation function that converts a vector of raw scores into a probability distribution, where all values sum to 1. Softmax is typically used in the final layer of classification models and in attention mechanisms.

In practice

If a model outputs raw scores [2.0, 1.0, 0.1] for three classes, softmax converts them to probabilities [0.66, 0.24, 0.10].