Fix: improve Sigmoid efficiency and correct Softmax gradient computation#125
Open
PolarisMurray wants to merge 1 commit intoeriklindernoren:masterfrom
Open
Fix: improve Sigmoid efficiency and correct Softmax gradient computation#125PolarisMurray wants to merge 1 commit intoeriklindernoren:masterfrom
PolarisMurray wants to merge 1 commit intoeriklindernoren:masterfrom
Conversation
Sigmoid.gradient(): avoid redundant calls to self.__call__(x) → improves numerical stability and efficiency by computing sigmoid(x) once. Softmax.gradient(): replaced incorrect elementwise p*(1-p) derivative with correct Jacobian matrix form: J = diag(p) - outer(p, p) → ensures mathematically accurate gradients for multi-class outputs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Sigmoid.gradient(): avoid redundant calls to self.call(x)
→ improves numerical stability and efficiency by computing sigmoid(x) once.
View change in code
Softmax.gradient(): replaced incorrect elementwise p*(1-p) derivative with correct Jacobian matrix form: J = diag(p) - outer(p, p) → ensures mathematically accurate gradients for multi-class outputs.
View change in code