Microsoft Cognitive Toolkit

The Microsoft Cognitive Toolkit is a free, easy-to-use, open-source, commercial-grade toolkit that trains deep learning algorithms to learn like the human brain. The Microsoft Cognitive Toolkit—previously known as CNTK—empowers users to harness the intelligence within massive datasets through deep learning by providing uncompromised scaling, speed, and accuracy with commercial-grade quality and compatibility with the programming languages and algorithms users already use. The Microsoft Cognitive Toolkit, 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. Moreover, the Microsoft Cognitive Toolkit trains and evaluates deep learning algorithms faster than other available toolkits, scaling efficiently in a range of environments—from a CPU, to GPUs, to multiple machines—while maintaining accuracy. The Microsoft Cognitive Toolkit is also built with sophisticated algorithms and production readers to work reliably with massive datasets. Skype, Cortana, Bing, Xbox, and industry-leading data scientists already use the Microsoft Cognitive Toolkit to develop commercial-grade AI. The Microsoft Cognitive Toolkit offers the most expressive, easy-to-use architecture available. Working with the languages and networks users know, like C++ and Python, it empowers users to customize any of the built-in training algorithms, or use users’ own.