0
$\begingroup$

When calculating gradients for backpropagation, a surprising result is that the gradient of the weights in a ReLU-activated layer ends up being a diagonal matrix. I am seeking to understand how this makes sense intuitively, in terms of gradient descent.

Does this mean that weights in the non-diagonal positions don't have an impact on the loss? How could that be? Do these weights never get updated at all?

Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ Think of what what's a gradient of the linear activation $\endgroup$
    – Aksakal
    Commented Feb 28, 2018 at 2:37

1 Answer 1

Reset to default
0
$\begingroup$

a surprising result is that the gradient of the weights in a ReLU-activated layer ends up being a diagonal matrix

Well, it doesn't. You just initialized your weights with a diagonal matrix.

Improve this answer
$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.