Kaspersky invests in neuromorphic processors dev’t used in next-gen smart devices

0
2

Cybersecurity leader Kaspersky announced that it has become a shareholder of Motive Neuromorphic Technologies, a company specializing in neuromorphic computing technologies.

With a 15% stake, this new investment aimed to create new opportunities for machine learning-based solutions: self-learning systems and smart devices of the future.

“For Kaspersky, access to these neuromorphic technologies paves the way for a global technology ecosystem. In the future, we will add hardware solutions based on neuromorphic processors to our proprietary operating system, KasperskyOS – a full set of software for countering cyberthreats, as well as the MyOffice suite,” said Andrey Doukhvalov, VP, Future Technologies at Kaspersky.

Kaspersky concluded a cooperation agreement with Motive NT in 2019 to develop the Altai neuromorphic processor that accelerates the systems’ hardware using Machine Learning. The companies’ specialists banded together to create the first batch of neuromorphic processors that successfully performed speed and energy efficiency through experimentation.

Now, the companies are working on developing the second version of the neuromorphic processor, searching for technological partners for joint pilot projects with the Altai neurochip.

When commercialized, the Altai neurochip can make neural network training technologies more efficient and accessible for many devices and reduce energy costs. That is because, unlike the ordinary processors, Altai neurochip does not need to access and extract from memory (or registers) when all the information is already stored in artificial neurons. Similar to a human brain, the chip can process big data without the need for additional computing power on end devices. 

“Neuromorphic processors’ field of application is an acceleration of the hardware used in the latest generation of artificial intelligence systems, which are based on spiking neural networks (SNN) training. This approach is more akin to biological interactions – whereas, traditionally, artificial neural networks (ANN) exchange numbers – neuromorphic processors enable them to operate like biological neurons, communicating through spikes,” explained Alexey Romanov, CEO of Motive NT.

From multiple testing, the Altai processor showed to consume almost 1000 times less energy than traditional graphics accelerators (GPUs), which are widely used today.

According to Romanov, the investment opens opportunities for developing highly energy-efficient solutions. He foresees that the neuromorphic processors will be in demand in multiple areas, including the Internet of Things (IoT), robotics, unmanned vehicles, AR projects, cyber-physical security systems, face recognition, intelligent processing of big data, and so much more.

“The development of this technology could very well stimulate the emergence of completely new devices and technologies, because of its adaptability and the new generation of training algorithms it brings,” added Romanov.

Interested to read more about the development of the neuromorphic processors can visit Motive NT at http://www.motivnt.ru/.