Microsoft today announced they are making their CNTK deep-learning toolkit available as open-source via GitHub. They describe it as, "CNTK is a unified computational network framework that describes deep neural networks as a series of computational steps via a directed graph. In a directed graph, each node represents an input value or a network parameter, and each edge represents a matrix operation upon its children. CNTK provides algorithms to carry out both forward computation and gradient calculation. Most popular computation node types are predefined and users can easily extend node types under the open source license."
Microsoft claims that CNTK is more efficient than Theano, TensorFlow, Torch 7, and Caffe as other alternatives. The Computational Network Toolkit (CNTK) is GPU accelerated using CUDA and can be downloaded today from GitHub under the MIT license. CNTK does appear to be support Linux. More details via this Microsoft blog post.