0
$\begingroup$

I want to use skip connection in a Dense model and I chose the following implementation of the idea:

enter image description here

That is I use a Dense layer with linear activation to map the input into a dimension that will allow me to add it with the activation of the latest layer.

Is this the most effective way to implement the idea of skip-residual connections in a dense network?

$\endgroup$

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.