hantek

BinaryConnect

Source code for ``Neural Networks with Few Multiplications'' published at ICLR 2016

zlinnet

Source code for ``How far can we go without convolution: Improving fully-connected networks'' published at ICLR 2016 workshop

NeuroBricks

A theano wrapper for conveniently implementing, training and analyzing neural nets.

parikh_snli

A lasagne reproduction of Parikh's decomposable attention model, ``A Decomposable Attention Model for Natural Language Inference'' published at EMNLP 2016

binary_conv

binary connected convolutional nets

tree_rnn

Theano implementation of Tree RNNs aka Recursive Neural Networks.

complex_RNN

debugger.lua

A simple, embedabble CLI debugger for Lua.

fblualib

Facebook libraries and utilities for Lua

fuel

A data pipeline framework for machine learning

Lasagne

Lightweight library to build and train neural networks in Theano

learn-travis

:sunglasses: A quick Travis CI (Continuous Integration) Tutorial for Node.js developers

localnet

mxnet

Lightweight, Portable, Fast and Flexible Distributed Deep Learning, for python, R, Julia, Go and more

OnchipBNN

Trying to put Binary Neural Network on a chip

pylearn2

A Machine Learning library based on Theano

Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

treelstm

Tree-structured Long Short-Term Memory networks (http://arxiv.org/abs/1503.00075)

zaesrnn

srnn architecture using zae as activation function

zmlp