Microsoft Releases Second Update of Its Deep Learning Toolkit

Posted By : Anirudh Bhardwaj | 22-Jun-2017

Machine Learning Toolkit by Microsoft

After months of beta testings, Microsoft has finally launched the second version of its highly acclaimed deep learning toolkit. Microsoft Cognitive Toolkit as it’s called, is a free and open-source commercial grade toolkit that is used for devising deep learning algorithms. Formerly known as CNTK, it enables you harness the intelligence of deep learning by means of uncompromised scaling, speed and accuracy. With the version 2.0, Microsoft seems to be catching up with the competitors like Google and is very much similar to the deep learning tools such as TensorFlow, Torch and Caffe. While the first version couldn’t have a lasting effect on the developers, the version 2.0 can prove to be a game-changer in this field.   

 

The version 2.0 however, will have its main focus on usability. With added support for Python and Keras neural networking library, Microsoft Cognitive Toolkit v2.0 is ready to revitalize the Machine Learning development landscape. The company had been running numerous beta tests on this Cognitive toolkit since October 2016 and as it turns out, it’s finally ready for production use.

 

You may also like Machine Learning Will Help Improve Google Maps Services.

 

Downsides of Version 1.0

As revealed by the technical core team at Microsoft, the version 1.0 was primarily meant for open sourcing the internal toolkit of Microsoft, thereby making it accessible to the masses. One of the major setbacks in the previous version was that it didn’t support Python even though it is the most extensively used programming language by the Machine Learning developers.  

 

As a matter of fact, the version 1.0 was primarily built for the speech recognition systems and interestingly, it worked exceptionally well with time series data and is still widely used for building recurrent neural networks. Of course, the Microsoft team has improved the performance of Cognitive Toolkit for all kinds of neural networks. In addition to that, it has now become easier to extend the system in a long run.

 

 

Other Notable Features

The new Cognitive Toolkit by Microsoft version 2.0 also supports Java language bindings for model evaluation and it will offer many new tools for enabling trained models to run on many low-powered devices such as smartphones and tablets.

 

Microsoft itself is using its new Cognitive Toolkit as of now while there are several groups in the company that are also using other toolkits. As a matter of fact, all the leading tech savvy companies are taking keen interest in Artificial Intelligence and Machine Learning these days. Clearly, Microsoft doesn’t want to leave any stone unturned with its new Cognitive Toolkit version 2.0 which is all set to hit the market.

 

About Author

Author Image
Anirudh Bhardwaj

Anirudh is a Content Strategist and Marketing Specialist who possess strong analytical skills and problem solving capabilities to tackle complex project tasks. Having considerable experience in the technology industry, he produces and proofreads insightful content on next-gen technologies like AI, blockchain, ERP, big data, IoT, and immersive AR/VR technologies. In addition to formulating content strategies for successful project execution, he has got ample experience in handling WordPress/PHP-based projects (delivering from scratch with UI/UX design, content, SEO, and quality assurance). Anirudh is proficient at using popular website tools like GTmetrix, Pagespeed Insights, ahrefs, GA3/GA4, Google Search Console, ChatGPT, Jira, Trello, Postman (API testing), and many more. Talking about the professional experience, he has worked on a range of projects including Wethio Blockchain, BlocEdu, NowCast, IT Savanna, Canine Concepts UK, and more.

Request for Proposal

Name is required

Comment is required

Sending message..