softmax - AshokBhat/ml GitHub Wiki

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

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

• For multi-class classification tasks

• 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.

• Activation function : ReLU | Softmax | Sigmoid | Tanh