Skip to content

Instantly share code, notes, and snippets.

@cosmic-cortex

cosmic-cortex/differentiable_sigmoid.py Secret

Created October 23, 2019 07:56
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save cosmic-cortex/3d8c13f3013750239a558233748a9988 to your computer and use it in GitHub Desktop.
Save cosmic-cortex/3d8c13f3013750239a558233748a9988 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
differentiable_sigmoid.py
class Sigmoid(Function):
def forward(self, X):
return 1/(1 + np.exp(-X))
def backward(self, dY):
return dY * self.grad['X']
def local_grad(self, X):
s = 1/(1 + np.exp(-X))
grads = {'X': s * (1 - s)}
return grads
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment