Gary Wang's repositories
Matlab_LSTM
practice lstm implementation in Matlab
annabell
A cognitive neural architecture able to learn and communicate through natural language
backtrader
Python Backtesting library for trading strategies
ccmsuite
Python cognitive modelling suite
char-rnn-tensorflow
Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow
CNTK
Computational Network Toolkit (CNTK)
convnetjs
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
Cortexsys
Matlab and Octave GPU Accelerated Deep Learning Toolbox
dcgan_code
Deep Convolutional Generative Adversarial Networks
Deep_Neural_Fun
For self learning, develop a modular neural network library, with FF and Recurrent components
deep_q_rl
Theano-based implementation of Deep Q-learning
deepmat
Matlab Code for Restricted/Deep Boltzmann Machines and Autoencoders
Dynamic-memory-networks-in-Theano
Implementation of Dynamic memory networks by Kumar et al. http://arxiv.org/abs/1506.07285
flappy-bird-pygame
A clone of Flappy Bird, using Pygame.
Human_Level_Control_through_Deep_Reinforcement_Learning
Deepmind's Deep Q Learning on Atari
Mario-Level-1
The first level of Super Mario Bros made with Python and Pygame.
MemNN
Memory Networks implementations
nmn2
Dynamically predicted neural network structures for multi-domain question answering
pyoanda
Oanda’s API python wrapper. Robust and Fast API wrapper for your Forex bot Python library that wraps Oanda API. Built on top of requests, it’s easy to use and makes sense.
python-rl
Some Reinforcement Learning in Python
simple_dqn
Simple deep Q-learning agent.
text-world
Python MUD/MUX/MUSH/MU* development system
text-world-player
Framework and model code for the paper "Language Understanding for Text-based Games using Deep Reinforcement Learning", EMNLP 2015
theano_lstm
:microscope: Nano size Theano LSTM module
ualbertabot
UAlbertaBot
Windy-Grid-World-Q-Learning
Matlab implementation of Windy grid world Q learning approach using greedy policy.