statistical shot distribtuions #387
Open
Conversation
This file contains 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
Why? ReLU layers without bias are input scale-invariant (they're just multiplies and thresholds at zero). So this doesn't care if the ratings are near 20 or near 80... it can't tell the difference. I needed the extra layers to get comparable performance. Although it is slightly worse in terms of loss, I think being input scale invariant is a huge win.
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Outdated suggestions cannot be applied.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.
The script to generate the model is in https://github.com/nicidob/bbgm/blob/master/shooting_stats.ipynb
I re-created this PR because there were some conflicts that I hopefully resolved. Plus there's a husky bug fix in here.