Softmax - AshokBhat/ml GitHub Wiki

Softmax Layer

Description

  • An activation function
  • To transform the output of the neural network into a probability distribution over the possible classes

What does it do?

  • Turns logits into probabilities that sum to one
  • Output is a vector that represents the probability distributions of a list of potential outcomes.

Usage

  • For multi-class classification tasks

FAQ

  • What is SoftMax?
    • An activation function
  • What does it do?
    • Turns input logits into probabilities that sum to one
  • What does the output represent?
    • A vector that represents probability distributions of a list of potential outcomes.

See also