0

I want to implement a neural network on pytorch where gradients are not computed over all the weights. Let's say for example I have an MLP with three layers and I want half of the nodes in the last layer to have their backpropagation computed all the way up to the first layer but the other half of the last layer have their gradients computed only up to the middle layer. I would be grateful for any help. Thanks

Improve this question
2
  • What actually means 'not computing', just skipping the gradient or replacing to another? Commented Feb 3 at 9:06
  • It means the error in the 2nd half of the nodes in the last layer will be used to update the weights from the middle layer to the last layer but will not affect the weights from the first to the middle layer Commented Feb 4 at 9:58
Related questions
1869
How can I import a module dynamically given the full path?
1787
How do I get the filename without the extension from a path in Python?
5
Siamese Neural Network in Pytorch
Load 6 more related questions Show fewer related questions

0

Reset to default

Your Answer

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

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.