Image Super-Resolution for Anime-Style Art

Torch implementation of neural style algorithm

Face recognition with deep neural networks.

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Feedforward style transfer

Facebook AI Research Sequence-to-Sequence Toolkit

棋牌的胡牌算法，包括麻将、跑胡子、扑克。实现 lua 、c++ 、c# 、golang 、js 、java 、python 版本。( Mahjong algorithm )

Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others.

The original code from the DeepMind article + my tweaks

Memory Networks implementations

A torch implementation of http://arxiv.org/abs/1511.06434

Facebook's extensions to torch/cunn.

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

❔ Visual Question Answering in Torch

Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)

source code for the paper Deep Knowledge Tracing

Code for Kaggle-CIFAR10 competition. 5th place.

Simple Baseline for Visual Question Answering

Capsule network with variations. Originally proposed by Tieleman & Hinton : http://www.cs.toronto.edu/~tijmen/tijmen_thesis.pdf

广东四川麻将的吃碰杠听胡逻辑以及广东麻将简易的AI实现

Entry for GalaxyZoo challenge

FDF files for relaxation, PDOS and Denchar calculations in SIESTA 4.0.2 version as well as 4.1v and PSML supported version

Work in progress. Read at your own risk.

Code use for Galaxy Zoo competition on kaggle

Interfacing SIESTA to Lua scripts using the flook code