Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[math] change the internal implementation of surrogate function #562

Merged
merged 3 commits into from
Dec 22, 2023

Conversation

chaoming0625
Copy link
Collaborator

Description

  • add heaviside_p primitive
  • all surrogate functions (with one argument) support both JVP (forward) and VJP (backward) differentiations
  • enabling the forward gradients of spiking neural networks

How Has This Been Tested

Yes.

…rimitive, so that all surrogate functions support JVP (forward) and VJP (backward) differentiation
@chaoming0625 chaoming0625 merged commit bf6f87e into master Dec 22, 2023
32 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant