俞航's repositories
Feedback-Alignment
Feedback alignment is a backpropagation modification where the next layer weights become a fixed random matrix. [Lillicrap et al](https://www.nature.com/articles/ncomms13276) shows a FA is a regularizer where the next layer weights must learn to orient within 90 degree in order to perform effective training. The main obstacle of FA is to prove of general convergence under nonlinear dynamics.
MSL-VirtualMorrisWaterMaze
This repository contains the Unity project for the Memory Systems Lab version of the Virtual Morris Water Maze.
reversi-alpha-zero
Reversi reinforcement learning by AlphaGo Zero methods.
adv_attack_capsnet
Tensorflow Implementation of Adversarial Attack to Capsule Networks
benchmarks
Benchmark code
chess-alpha-zero
Chess reinforcement learning by AlphaGo Zero methods.
docker_practice
Learn and understand Docker technologies, with real DevOps practice!
Matrix-Capsules-EM-Tensorflow
A Tensorflow implementation of CapsNet based on paper Matrix Capsules with EM Routing
multiagent-competition
Repository for competitive multi-agent environments
stanford-tensorflow-tutorials
This repository contains code examples for the course CS 20SI: TensorFlow for Deep Learning Research.
asyncio-doc
Asyncio documentation
awesome-asyncio
A curated list of awesome Python asyncio frameworks, libraries, software and resources
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
CapsNet-Keras
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error = 0.34%.
CondenseNet
CondenseNet: An Efficient DenseNet using Learned Group Convolutions
deep-learning-model-convertor
The convertor/conversion of deep learning models for different deep learning frameworks/softwares.
deep-visualization-toolbox
DeepVis Toolbox
Distributed-TensorFlow-Guide
Distributed TensorFlow basics and examples of training algorithms
GAN-mnist
This is my implementation on GAN in order to test my understanding. The result is pleasant.
keras-cntk-docker
Docker container for keras + cntk intended for nvidia-docker
leela-zero
Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.
mc-chess
MCTS chess engine, just for kicks
really-awesome-gan
A list of papers on Generative Adversarial (Neural) Networks
zhusuan
A Library for Bayesian Deep Learning, Generative Models, Based on Tensorflow