fix: Change embeddings matrix shape to (E,I) on RNN #234
Conversation
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
Remove usage of reserved keyword "input".
vascosmota
changed the title
Member
|
I think the overloading of "input" is fine in this context. I'd rather keep the naming consistent. can you move this PR to master? (sorry for the late response) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
On Algorithms 9 and 10, the embeddings matrix$\mathbf{W}^e \in \mathbb{R}^{E \times I}$ was shape $(E, I)$ . The initialization of the RNN on $\mathbf{W}^e$ with shape $(I, E)$
lxmls/deep_learning/rnn.pyinitializes a(input_size, embedding_size)instead.This change makes$\mathbf{W}^e$ have shape $(E, I)$ and also updates the
NumpyRNN.log_forwardmethod to account for the new shape.Also on this PR is the rename of the argument
input(a python builtin function) to `model_input* across multiple functions. Maybe we want to move this to a different PR.