Feat/autodiff nn - #1
Open
KellyKinyama wants to merge 4 commits into
Open
KellyKinyama wants to merge 4 commits into
KellyKinyama wants to merge 4 commits into
Conversation
Add scale() and axis-explicit addVector/subtractVector/multiplyVector/divideVector to Matrix64/Matrix32, plus Vector64/Vector32 scale(), giving a fully typed multiply path and removing the square-matrix broadcast ambiguity.
Add Variable (reverse-mode AD over Matrix64) with matmul/elementwise/activations/reductions, broadcast-with-reduce addRowVector, and memory-saving graph freeing in backward(). Add nn module: Module/Linear/ReLU/Tanh/Sigmoid/Sequential and SGD (with momentum)/Adam optimizers. Pure CPU on the existing SIMD kernels; no FFI.
Author
|
autodiff |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
added automatic differentiation