Glossary term
Glossary term
Foundations
A function that determines probabilities for each possible class in a multi-class classification model. The probabilities add up to exactly 1.0. For example, the following table shows how softmax distributes various probabilities:
Softmax is also called full softmax.
Contrast with candidate sampling.
Click the icon to see the math.
See Neural networks: Multi-class classification in Machine Learning Crash Course for more information.
Created for this library
An NLP team uses softmax at the output of its classifier to produce probabilities over 20 ticket categories.
A retail team uses softmax over a small set of payment methods as the output of its checkout model.
A research team uses softmax with temperature to control the entropy of the output distribution during sampling.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License