THIS IS A TEST INSTANCE ONLY! REPOSITORIES CAN BE DELETED AT ANY TIME!

Migrate from GitHub
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
Piotr Kozakowski b14a07cab0 Write documentation 4 years ago
examples Add an RNN example 4 years ago
images Write documentation 4 years ago
.gitignore Initial commit 4 years ago
LICENSE Initial commit 4 years ago
README.rst Write documentation 4 years ago
dni.py Write documentation 4 years ago
setup.py Implement DNI and a MNIST MLP example 4 years ago

README.rst

Decoupled Neural Interfaces for PyTorch
=======================================

This tiny library is an implementation of
`Decoupled Neural Interfaces using Synthetic Gradients <https://arxiv.org/abs/1608.05343>`_
for `PyTorch <http://pytorch.org/>`_.
It's very simple to use as it was designed to enable researchers to integrate
DNI into existing models with minimal amounts of code.

To install, run::

$ python setup.py install

Description of the library and how to use it in some typical cases is provided
below. For more information, please read the code.

Terminology
-----------

This library uses a message passing abstraction introduced in the paper. Some
terms used in the API (matching those used in the paper wherever possible):

- ``Interface`` - A Decoupled Neural Interface that decouples two parts (let's
call them part A and part B) of the network and lets them communicate via
``message`` passing. It may be ``Forward``, ``Backward`` or
``Bidirectional``.
- ``BackwardInterface`` - A type of ``