https://github.com/ypxie/pytorch-NeuCom

Pytorch implementation of DeepMind's differentiable neural computer paper.
https://github.com/ypxie/pytorch-NeuCom

Last synced: 7 months ago
JSON representation

Pytorch implementation of DeepMind's differentiable neural computer paper.

• Host: GitHub
• URL: https://github.com/ypxie/pytorch-NeuCom
• Owner: ypxie
• Created: 2017-02-13T03:55:45.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2017-12-04T23:24:31.000Z (almost 8 years ago)
• Last Synced: 2024-12-10T16:44:19.403Z (11 months ago)
• Language: Python
• Homepage:
• Size: 193 KB
• Stars: 94
• Watchers: 8
• Forks: 15
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-pytorch-list-CNVersion - pytorch-NeuCom - Z7E6X_a9R-xqJ9TfJWBqz)。 (Paper implementations｜论文实现 / Other libraries｜其他库:)
• Awesome-pytorch-list - pytorch-NeuCom

README

          
# DNC pytorch

This is a Pytorch implementation of DeepMind's Differentiable Neural Computer (DNC) architecture introduced in their recent Nature paper:

> [Graves, Alex, et al. "Hybrid computing using a neural network with dynamic external memory." Nature 538.7626 (2016): 471-476.](http://www.nature.com/articles/nature20101.epdf?author_access_token=ImTXBI8aWbYxYQ51Plys8NRgN0jAjWel9jnR3ZoTv0MggmpDmwljGswxVdeocYSurJ3hxupzWuRNeGvvXnoO8o4jTJcnAyhGuZzXJ1GEaD-Z7E6X_a9R-xqJ9TfJWBqz)

## Local Environment Specification

pytorch

Anaconda 2.7

## How To Run

Go to folder tasks/Copy

`python train.py`

## Dynamic Memory Mechanisms

![DNC-Memory-Mechanisms](/figures/dnc_digram.png)

## Acknowlegement

Mostafa-Samir's [tensorflow implementation](https://github.com/Mostafa-Samir/DNC-tensorflow)

## License

MIT