A visualization of the internal dynamics of a character-lever Recurrent Neural Network (RNN) during training, prediction, and generation.
Uses recurrentjs.
Heavily adapted from the character-level demo in the recurrentjs repository.
MIT
forked from karpathy/recurrentjs
-
Notifications
You must be signed in to change notification settings - Fork 1
kdbanman/recurrentjs
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Deep Recurrent Neural Networks and LSTMs in Javascript. More generally also arbitrary expression graphs with automatic differentiation.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- HTML 63.8%
- JavaScript 33.7%
- CSS 2.5%