How To Train Your AI: Microsoft Releases Open-Source Deep Learning Software

High-Tech and Flexible

Ever wanted to develop your own artificially-intelligent programs? Microsoft is empowering everyone with the capability to create huge, intelligent data-processing systems with the release of the Cognitive Toolkit.

The Cognitive Toolkit—previously known as CNTK—is a superfast deep-learning toolkit that brings commercial-grade quality and processing accuracy together with programming languages and algorithms you already use.

 

The Cognitive Toolkit utilizes "neural networks" to crunch large data sets across multiple machines. It's not just for developers with a farm of servers and GPUs, though—hobbyists and modest users can be equally competitive because the Toolkit is flexible enough to run on a single laptop. Developers can also integrate into the Toolkit their own Python or C++ code.

It's a technology made for startup developers and modest machines, but Microsoft claims that it's not in anyway a step back in quality. The Cognitive Toolkit is the same technology from the company's AI division that brought to us developments like the Skype Translator and Cortana. Fast-learning speech-recognition engines that "listen" as well as humans can have been developed by the same tools.

Microsoft claims that the Cognitive Toolkit's beta version—available now on GitHub —is faster than not only its previous versions, but also most of the other competing deep-learning toolkits.

Democracy of Knowledge

The release of a quality open-source data-processing toolkit is revolutionary in addressing how people can learn and develop technology. Xuedong Huang, an engineer from Microsoft, called the release "democratizing."

Deep learning systems have been used in simple developments with large impact. Refrigeration company Liebherr has used the Microsoft Cognitive Toolkit to decrease food waste using a smart app that lets you know what's inside your refrigerator. Development such as this could improve lives if they're just equipped with the right tools.

Big data analytics and AI development could be for everyone, not just the software development giants. With more minds given access to better tools, technological breakthroughs are just waiting to be made.