softmax activation

Softmax is a mathematical function that converts a vector of numbers into a vector of probabilities. The network is configured to output N values, one for each class in the classification task, and the softmax function is used to normalize the outputs, converting them from weighted sum values into probabilies that sum to one.

Softmax is used as activation function for multi-calss classification problems, it usually be used in a neural network model.

A neural network model requires an activation function in the output layer of the model to make the prediction of multinomial probability distribution.