-
Notifications
You must be signed in to change notification settings - Fork 23
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
nice project #1
Comments
Hi hardmaru, Nice to hear from you! I read your blog posts before - they were awesome! Let me fork your project and check it out on Sunday :) By the way - I found your comment about the number of the inner loops in Best, |
Cool! I think my implementation is not exactly correct as I had some difficulties understanding the paper. If you want to discuss more later on, feel free to swing by mountain view as well. I'm generally interested in working on these concepts relating to self-modifying weights inside RNNs. |
Sure. I can swing by some time next weekend! On Sat, Oct 29, 2016 at 3:42 PM hardmaru notifications@github.com wrote:
|
The implementation for RNNCell is here: d98097e |
Hi, you guys might be interested in this https://github.com/jxwufan/AssociativeRetrival |
Thanks. |
Hi Jiamings,
Nice to see an implementation of fast weights! I've also been working on one (at the bottom of https://github.com/hardmaru/supercell/blob/master/supercell.py), but unfortunately haven't done extensive testing yet.
Would you care to write an implementation that works as an RNNCell? That would be more useful to plug into other experiments (such as character prediction).
Happy to discuss further!
The text was updated successfully, but these errors were encountered: