Create gru.py#176
Open
jackru wants to merge 6 commits into
Open
Conversation
This is my first pull request to github, so please let me know if I've done something terribly wrong! I think the maths in this implementation checks out - I couldn't find a proof anywhere else, so I derived it myself. PS obviously borrows heavily from LSTMLayer.py
I realised that "peep" weights were only feeding back information from the neuron itself (as opposed to whole previous hidden state of the entire layer). This should fix it - layer now contains 3 * n ** 2 peep weights.
Fixed error in _setDerivatives
Some maths errors fixed - now satisfies gradientCheck().
Some final maths changes I forgot in the last commit plus tidying up.
More tidying up
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This is my first pull request to github, so please let me know if I've done something terribly wrong!
I think the maths in this implementation checks out - I couldn't find a proof anywhere else, so I derived it myself.
PS obviously borrows heavily from LSTMLayer.py