CNTK swMATH ID: 21056 Software Authors: Microsoft; Frank Seide; Amit Agarwal Description: The Microsoft Cognitive Toolkit (https://cntk.ai), is a unified deep-learning toolkit that describes neural networks as a series of computational steps via a directed graph. In this directed graph, leaf nodes represent input values or network parameters, while other nodes represent matrix operations upon their inputs. CNTK allows to easily realize and combine popular model types such as feed-forward DNNs, convolutional nets (CNNs), and recurrent networks (RNNs/LSTMs). It implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers. CNTK has been available under an open-source license since April 2015. It is our hope that the community will take advantage of CNTK to share ideas more quickly through the exchange of open source working code. Homepage: https://github.com/Microsoft/CNTK Source Code: https://github.com/Microsoft/CNTK Related Software: TensorFlow; Caffe; MXNet; PyTorch; Theano; Torch; Keras; Python; DiffSharp; Orange; Scikit; Chainer; Numba; gputools; PyOpenCL; Sun Grid Engine; OpenCL; Julia; CUSPARSE; R Cited in: 3 Publications all top 5 Cited by 9 Authors 1 Arbabifard, Kamyar 1 Baydin, Atılım Güneş 1 Gudivada, Venkat N. 1 Ko, Seyoon 1 Pearlmutter, Barak A. 1 Radul, Alexey Andreyevich 1 Siskind, Jeffrey Mark 1 Won, Joong-Ho 1 Zhou, Hua Cited in 2 Serials 1 Statistical Science 1 Journal of Machine Learning Research (JMLR) Cited in 3 Fields 1 Statistics (62-XX) 1 Numerical analysis (65-XX) 1 Computer science (68-XX) Citations by Year