Differentiable Neural Computer in TensorFlow

deepmind differentiable-computing dnc jupyter-notebook nature neural-network tensorflow

Go to file

Sam Greydanus c8068e8ace free recall results look good		2017-03-01 12:49:41 -05:00
dnc	yeah it's lit	2017-02-26 20:45:35 -05:00
free-recall	free recall results look good	2017-03-01 12:49:41 -05:00
handwriting	serial-recall task	2017-02-28 22:11:13 -05:00
repeat-copy	serial-recall task	2017-02-28 22:11:13 -05:00
static	serial-recall task	2017-02-28 22:11:13 -05:00
README.md	just little error fix	2017-02-21 17:19:17 -05:00

README.md

DNC: Differentiable Neural Computer

Implements DeepMind's third nature paper, Hybrid computing using a neural network with dynamic external memory by Graves et. al.

Based on the paper's appendix, I sketched the computational graph

I got the repeat-copy task to work (Jupyter notebook)

This is a work in progress

I have a general framework and a couple Jupyter notebooks for debugging. This is not a finished project. It's still very much in the dev stage. I need to:

write unit tests
improve documentation/comments
run it on more difficult tasks
add some nice visualizations

Dependencies

All code is written in python 2.7. You will need:
Numpy
Matplotlib
TensorFlow r1.0