Conversation
wdotmathree
requested changes
Aug 9, 2026
Bench: 2312312
Bench: 2312312
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Dual activation involves changing the L1->L2 activation from a single SCReLU to both CReLU and CSReLU. By combining two different activation functions, we are able to encode more information. Because we don't change the L1->L2 weights, the computational cost is minimal for a reasonable gain in evaluation accuracy.
The effective size of L2 therefore changes from 16 neurons to 32 neurons, where the first 16 are activated by CReLU and the latter 16 are activated by CSReLU. Thus, the L2->L3 transformation becomes a 32x32 matrix multiplication and the number of weights in that layer doubles.