Analog platform uses memristors for AI in edge devices

December 11, 2019 // By Jean-Pierre Joosting
Analog platform uses memristors for AI in edge devices
The successful development of a breakthrough technological platform that uses memristor devices featuring analog memory storage and computing capabilities has been announced by TowerJazz and the Technion, the Israel Institute of Technology.

Based on commercial CMOS, the memristor based platform uses TowerJazz’s commercial patented Y-Flash NVM on its well-established 0.18um CMOS technology.

The technology enables development of ultra-low power Artificial Intelligence (AI) cores suitable for IoT edge devices and sensors such as fingerprint sensors, face and audio recognition applications among others. Compared with existing digitally based solutions, this breakthrough enables several orders of magnitude lower power consumption and is very cost effective as it can be implemented in less advanced technology nodes.

The extensive research and development was co-led by teams from both TowerJazz and the Technion. The complete research paper was published in Nature Electronics, and is the first research project conducted solely in Israel covered by Nature Electronics.

“With advanced R&D being our major focus, we are constantly seeking emerging technologies and initiate development projects to enrich TowerJazz’s offering,” said Prof. Yakov Roizin, TowerJazz’s Fellow.

“The collaboration between our professional academic team and our extensive research capabilities along with TowerJazz’s team, analog expertise and technology, is what enabled to realize this extraordinary result, ” said Prof. Shahar Kvatinsky of the Andrew & Erna Viterbi Faculty of Electrical Engineering at the Technion. “We are confident that the joint effort of experts from both fields will yield more significant achievements in years to come .”

Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.