I am trying to map my basic understanding of MLP's to CNN's. Why does a CNN sacrifice all negative inputs with the ReLU over the sigmoid. Is it because:

The sigmoid has a range of between zero and 1 which is worse for CNN's than 0 to infinity.

Is it to do with the fact the function only has one horizontal asymptote?

The negative inputs are meaningless? Or to speed up computation? Implied here on this question.

Any help is a appreciated.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.