- TDK's real-time analog chip is trained on advanced robotics and sensor technologies.
- The demo demonstrates high-speed learning in a rock-paper-scissors game.
- The neuromorphic approach aims to combine sensors and artificial intelligence for edge computing.
To most people, TDK is best known for its audio cassettes, which were a staple of home recording and personal music collections throughout the 1980s and 1990s.
Once synonymous with blank tapes and magnetic materials, the company has since grown into a major developer of advanced electronics and sensor technologies.
Now TDK, in collaboration with Hokkaido University, has developed a prototype analog AI reservoir chip he says he is capable of real-time learning.
Rock-paper-scissors
The technology mimics the human cerebellum and processes time-varying data at high speed and ultra-low power consumption, making it suitable for robotics and human-machine interfaces.
By learning directly at the edge and using analog circuits to calculate reservoirs, it differs from traditional deep learning models that rely on cloud processing and rich data sets.
Silicon exploits the natural physical dynamics of analog signals, such as wave propagation, to efficiently interpret, input, and create output data with minimal power.
TDK says the prototype's ability to learn in real time will allow it to quickly adapt to changing data streams, making it well suited for applications that require instant feedback, such as wearables, autonomous systems and IoT equipment.
The company will unveil the prototype at the upcoming CEATEC 2025 event in Japan, where the demo device will challenge attendees to a game of rock-paper-scissors, using acceleration sensors to track hand movements and predict a winning gesture before the player gets a chance to complete their turn.
“In the game of rock-paper-scissors, there are individual differences in finger movement, and in order to accurately determine what to do next, it is necessary to study these individual differences in real time,” TDK explained.
“This demo device is attached to users' hands, finger movement is measured by an acceleration sensor, and the simple task of deciding what to play with rock-paper-scissors is processed in real time and at high speed on an analog AI tank, allowing users to realize an unwinnable 'rock-paper-scissors' concept.”
The company said it hopes the prototype chip demonstration will “contribute to broader understanding of reservoir computing” and that it will lead to accelerated commercialization of reservoir computing devices for edge AI applications.
The new design builds on TDK's earlier research into neuromorphic devices, which attempted to mimic the brain using spintronics.
Instead of performing heavy computational tasks, this analog reservoir AI is designed to quickly process time series data with low power consumption, making it ideal for edge sensing and control.
TDK says it plans to expand its collaboration with Hokkaido University and apply the results to its sensor systems business and the TDK SensEI brand.
By using Similar to eeNews
Follow TechRadar on Google News. And add us as your preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the “Subscribe” button!
And of course you can also Follow TechRadar on TikTok for news, reviews, unboxing videos and get regular updates from us on whatsapp too much.
