Deep Learning Open Sources

下面這些都是比較優質的深度學習的open source，和大家一起分享下。

一、cuda-convnet

C++/CUDA implementation of convolutional (or more generally, feed-forward) neural networks. It can model arbitrary layer connectivity and network depth. Any directed acyclic graph of layers will do. Training is done using the back-propagation algorithm.

二、cuda-convnet2

Multi-GPU training support implementing data parallelism, model parallelism, and the hybrid approach described in One weird trick for parallelizing convolutional neural networks

三、caffe

Caffe: a fast open framework for deep learning. 

http://caffe.berkeleyvision.org/

四、Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

http://www.deeplearning.net/software/theano

五、pylearn2

A Machine Learning library based on Theano

六、deeplearning4j

Deep Learning for Java, Scala & Clojure on Hadoop, Spark & GPUs 

http://deeplearning4j.org

七、purine2

purine version 2. This framework is described in Purine: A bi-graph based deep learning framework

八、petuum

Petuum is a distributed machine learning framework. It aims to provide a generic algorithmic and systems interface to large scale machine learning, and takes care of difficult systems "plumbing work" and algorithmic acceleration, while simplifying the distributed implementation of ML programs - allowing you to focus on model perfection and Big Data Analytics. Petuum runs efficiently at scale on research clusters and cloud compute like Amazon EC2 and Google GCE.

九、dmlc

A Community of Awesome Distributed Machine Learning C++ Projects

There's lots of treasure of DL.