Thesis/dnc-jupyter
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Differentiable Neural Computer in TensorFlow
15 Commits 1 Branch 0 Tags 32 MiB
Jupyter Notebook 97%
Python 3%
fe43e55dc7
Go to file
Sam Greydanus fe43e55dc7 Update README
2017-03-27 14:55:26 -04:00
dnc yeah it's lit 2017-02-26 20:45:35 -05:00
free-recall serial recall updates 2017-03-01 18:11:23 -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 Update README 2017-03-27 14:55:26 -04:00

README.md

DNC: Differentiable Neural Computer

See blog post

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

Repeat copy results

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

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

Dependencies

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