Softmax Function
/ˈsɒftmæks/
An activation function that converts a vector of values into a probability distribution summing to 1.
In italiano: Funzione SoftmaxSoftmax is used in multi-class classification output layers. It exponentiates each value and normalizes by the sum, producing interpretable probabilities for each class.
Examples
- Multi-class classification
- Language model next-token prediction
- Image classification output