Torch implementation of neural style algorithm

Face recognition with deep neural networks.

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

Efficient, reusable RNNs and LSTMs for torch

Memory Networks implementations

Digital Estate Planning: The Game

Task generation for testing text understanding and reasoning

LSTM language model with CNN over characters

Autograd automatically differentiates native Torch code

Learning to Execute

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