Which activation function is most commonly used in the final layer of a multi-class classification neural network to produce a probability distribution?
Show answer
Softmax
The softmax function takes a vector of K real numbers and normalizes it into a probability distribution consisting of K probabilities proportional to the exponentials of the input numbers. The output values sum to one.
Also asked as:
- Which function normalizes a vector of real numbers into a probability distribution where the outputs sum to one, typically used in multi-class output layers?