Theano implementation of the paper One-shot Learning with Memory-Augmented Neural Networks, by A. Santoro et al.

To avoid any conflict with your existing Python setup, and to keep this project self-contained, it is suggested to work in a virtual environment with virtualenv. To install virtualenv:

sudo pip install --upgrade virtualenv

Create a virtual environment called venv, activate it and install the requirements given by requirements.txt.

virtualenv venv
source venv/bin/activate
pip install -r requirements.txt

In order to run the experiment on the Omniglot dataset, you first need to download the dataset in the data/omniglot folder (see the README for more details).

This projects has a few basic tests. To run these tests, you can run the py.test on the project folder

venv/bin/py.test mann -vv

Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, Timothy Lillicrap, One-shot Learning with Memory-Augmented Neural Networks, [arXiv]