Hi Kilian,

Good question. While getting the values to sum to 1 is one nice property of softmax, the other important property is that it squeezes the values into a sigmoid-like function. This squeezing is essential to categorial distributions, since it will push low or high values to 0 or 1.

PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store