I'm sort of confused as to how the nonlinearity of an activation function like the ReLu means that relatively complex mappings can all be approximated by a neural network? I guess I am sort of confused as to how neural networks are able to learn these functions in general.



marked as duplicate by Reinstate Monica, shimao, Michael R. Chernick, kjetil b halvorsen, mkt - Reinstate Monica Nov 29 '18 at 8:32

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

Browse other questions tagged or ask your own question.