I have come up with some examples of CNNs (segmentation CNNs) that use ELU (exponential linear unit) as an activation function.

What are the benefits of this activation function over others, such as RELU or leaky RELU?

  • 1
    $\begingroup$ Sigmoid returns a number between 0 and 1. If input is large, the gradient of the function give no useful information, since outside the 0-1 range the function is flat. in compare to sigmoid, the function like ELU and ReLU are not flat outside the range. take a look at the form of these functions $\endgroup$ – Aray Karjauv Nov 16 '20 at 12:03

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.