sheuan

BinaryNet-1

Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

minerva

Minerva: a fast and flexible tool for deep learning on multi-GPU. It provides ndarray programming interface, just like Numpy. Python bindings and C++ bindings are both available. The resulting code can be run on CPU or GPU. Multi-GPU support is very easy.

rocket-chip

Rocket Chip Generator

riscv-sodor

educational microarchitectures for risc-v isa

flexpret

CLM-framework

CLM-framework (a.k.a Cambridge Face Tracker) is a framework for various Constrained Local Model based face tracking and landmark detection algorithms and their extensions/applications. Includes CLM-Z and CLNF.

Lasagne

Lightweight library to build and train neural networks in Theano

BPL

Bayesian Program Learning model for one-shot learning

darknet

Convolutional Neural Networks

tf-play

brian2

Brian2 is an improved and partly rewritten version of Brian, the spiking neural network simulator (see http://briansimulator.org). It is currently in a beta state, ready for testing.

BinaryConnect

Training Deep Neural Networks with binary weights during propagations

openface

Face recognition with Google's FaceNet deep neural network.

hrr-scaling

Python/CUDA code to create a spiking neural network that can encode and traverse the Wordnet lexical database.

edlut

Automatically exported from code.google.com/p/edlut

iwae

Code to train Importance Weighted Autoencoders on MNIST and OMNIGLOT

SpiNNakerManchester.github.io

Organization Pages, Documentation and Issues

stdp-mnist

BrainComputerInterfaces

Variety of applications for BCI research

GaitLib

spiking_relu_conversion

skia

Skia is a complete 2D graphic library for drawing Text, Geometries, and Images.

rg-etc1

Automatically exported from code.google.com/p/rg-etc1

astc-encoder

auc-recognition

Automatically exported from code.google.com/p/auc-recognition

Single-Layer-CNN-on-MNIST

A single Layer CNN on MIST, get an acurray of 97.24%

chisel-tutorial

chisel tutorial exercises and answers

fooling

Code base for "Deep Neural Networks are Easily Fooled" paper

bci-challenge-ner-2015

Code and documentation for the winning solution at the BCI Challenge @ NER 2015 : https://www.kaggle.com/c/inria-bci-challenge