0
$\begingroup$

Say we have a convolutional neural network with an input layer, 3 convolutional layers and an output layer.

Say the gradients with respect to the weights and biases of the third convolutional layer are all 0.

Then, by backpropagation and the chain rule, does this necessarily mean that the gradients with respect to the weights and biases of the first two convolutional layers are 0 too?

Improve this question
$\endgroup$
1

0

Reset to default

Your Answer

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