-
Notifications
You must be signed in to change notification settings - Fork 0
More sensible back propagation #31
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
7910561 to
ed45645
Compare
Lucsanszky
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I have only found a minor typo so far but I will be keep reviewing tomorrow with a fresh pair of eyes.
Lucsanszky
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm not that familiar with the codebase to confidently approve this, but nonetheless I'll approve in case you are eager to merge. However, it would be good if @Soupstraw could review this too once he is back from his vacation.
Co-authored-by: Lucsanszky <[email protected]>
ddeab33 to
2dcfe17
Compare
Co-authored-by: Joosep Jääger <[email protected]>
closes #30
The idea here is that instead of having a bunch of special cases to deal with different configurations of
x == E[x']we generalize to propagating both backwards and forwards acrossE[x] == E'[x'], thus unifying previous cases and allowing many more specs to simply work out.