The CNTK Wiki has all information on CNTK including setup, examples, etc.

Effective January 25, 2017 CNTK 1-bit Stochastic Gradient Descent (1bit-SGD) and BlockMomentumSGD code is moved to a new Repository in GitHub.

Give us feedback through these channels.

Latest news

2017-02-01. V 2.0 Beta 10 Release

• New and updated core and Python API features (Operators with UserFunctions, Tensorboard support, Python API Fast R CNN).
• Improved speed of CrossEntropyWithSoftmax and ClassificationError for sparse labels.
• New Tutorials and Examples:
  • A Python version of the deconvolution layer and image auto encoder example was added (Example 07_Deconvolution in Image - Getting Started).
  • A Python distributed training example for image classification using AlexNet was added, cf. here
  • Basic implementation of Generative Adversarial Networks (GAN) networks
  • Training with Sampled Softmax
• New CNTK NuGet Packages.

See more in the Release Notes. Get the Release from the CNTK Releases page.

2017-01-25. V 2.0 Beta 9 Release available at Docker Hub
CNTK V 2.0 Beta 9 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

2017-01-25. 1bit-SGD Code is relocated to GitHub. Submodule configuration update is required for affected users
This news is related to users who are working with CNTK code base. If you use Binary or Docker Runtime Images installation you may ignore it.

Effective January 25, 2017 CNTK 1-bit Stochastic Gradient Descent (1bit-SGD) and BlockMomentumSGD code is moved to a new Repository in GitHub.

If you cloned CNTK Repository with 1bit-SGD enabled prior to January 25, 2017 you need to update git submodule configuration as described in this Wiki article.

2017-01-20. V 2.0 Beta 9 Release
Highlights of this Release:

• Default Python version is now 3.5 (relates to default parameters in client installations as well as Runtime Images at Docker Hub).
• New and updated core and Python API features.
• New Tutorials and Examples:
  • Deconvolution layer and image auto encoder example using deconvolution and unpooling (Example 07_Deconvolution in Image - Getting Started).
  • Basic autoencoder with MNIST data.
  • LSTM Timeseries with Simulated Data (Part A). (More will come in the next Releases)
• New CNTK NuGet Packages.

See more in the Release Notes.
Get the Release from the CNTK Releases page.

2017-01-19. V 2.0 Beta 8 Release available at Docker Hub
CNTK V 2.0 Beta 8 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

See all news.

What is The Microsoft Cognitive Toolkit

The Microsoft Cognitive Toolkit (https://www.microsoft.com/en-us/research/product/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. 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.

Wiki: Go to the CNTK Wiki for all information on CNTK including setup, examples, etc.

License: See LICENSE.md in the root of this repository for the full license information.

Tutorial: Microsoft Computational Network Toolkit (CNTK) @ NIPS 2015 Workshops

Blogs:

• Microsoft Computational Network Toolkit offers most efficient distributed deep learning computational performance
• Microsoft researchers win ImageNet computer vision challenge (December 2015)

Performance

The figure below compares processing speed (frames processed per second) of CNTK to that of four other well-known toolkits. The configuration uses a fully connected 4-layer neural network (see our benchmark scripts) and an effective mini batch size (8192). All results were obtained on the same hardware with the respective latest public software versions as of Dec 3, 2015.

Citation

If you used this toolkit or part of it to do your research, please cite the work as:

Amit Agarwal, Eldar Akchurin, Chris Basoglu, Guoguo Chen, Scott Cyphers, Jasha Droppo, Adam Eversole, Brian Guenter, Mark Hillebrand, T. Ryan Hoens, Xuedong Huang, Zhiheng Huang, Vladimir Ivanov, Alexey Kamenev, Philipp Kranen, Oleksii Kuchaiev, Wolfgang Manousek, Avner May, Bhaskar Mitra, Olivier Nano, Gaizka Navarro, Alexey Orlov, Hari Parthasarathi, Baolin Peng, Marko Radmilac, Alexey Reznichenko, Frank Seide, Michael L. Seltzer, Malcolm Slaney, Andreas Stolcke, Huaming Wang, Yongqiang Wang, Kaisheng Yao, Dong Yu, Yu Zhang, Geoffrey Zweig (in alphabetical order), "An Introduction to Computational Networks and the Computational Network Toolkit", Microsoft Technical Report MSR-TR-2014-112, 2014.

Disclaimer

CNTK is in active use at Microsoft and constantly evolving. There will be bugs.

Microsoft Open Source Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.