Microsoft Computational Network ToolKit – CNTK

34

Microsoft Cognitive Toolkitpreviously known as CNTK (Microsoft Computational Network ToolKit), is a deep learning framework developed by Microsoft Research. Microsoft Cognitive Toolkit describes neural networks as a series of computational steps via a directed graph.

A free, easy-to-use, open-source, commercial-grade toolkit that trains deep learning algorithms to learn like the human brain.

— Microsoft

Microsoft Cognitive Toolkit (formerly known as CNTK) version 2.0 is now available to Developers and Data Scientists. Cognitive Toolkit is a free, easy-to-use, open-source toolkit that trains deep learning algorithms to learn like the human brain. Learn more about the latest version of Cognitive Toolkit at https://aka.ms/CognitiveToolkit

  • Speed & Scalability
    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.
  • Commercial-Grade Quality
    The Microsoft Cognitive Toolkit is 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.
  • Compatibility
    The Microsoft Cognitive Toolkit offers the most expressive, easy-to-use architecture available. Working with the languages and networks you know, like C++ and Python, it empowers you to customize any of the built-in training algorithms or use your own.

See Microsoft Cognitive Toolkit