- TDK’s real-time analog chip learns at the edge for robotics and sensors
- Demo shows high-speed learning in a rock-paper-scissors challenge
- Neuromorphic approach aims to merge sensing and artificial intelligence for edge computing
To most people, TDK is best known for audio cassettes, which were a staple of home recordings and personal music collections during the 1980s and 1990s.
Once synonymous with blank tapes and magnetic materials, the company has since evolved into a major developer of advanced electronics and sensor technologies.
Now, TDK, in collaboration with Hokkaido University, has developed a prototype analog repository AI chip that it claims is capable of real-time learning.
rock-paper-scissors
The technology mimics the human cerebellum and processes time-varying data at high speed and with ultra-low power consumption, making it suitable for robotics and human-machine interfaces.
By learning directly at the edge and using analog circuits for reservoir computing, it differentiates itself from traditional deep learning models that rely on cloud processing and large data sets.
Silicon uses the natural physical dynamics of analog signals, such as wave propagation, to efficiently interpret, input, and produce outputs 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 uses that require instant feedback, such as wearable devices, autonomous systems and IoT hardware.
The company will present the prototype at the upcoming CEATEC 2025 event in Japan, where a demonstration device will challenge visitors to a game of rock, paper, scissors using acceleration sensors to track hand movement and predict the winning gesture before the player has a chance to complete their move.
“In rock, paper, scissors, there are individual differences in finger movement, and to accurately determine what to do next, you need to learn those individual differences in real time,” TDK explained.
“This demonstration device is placed in users’ hands, finger movement is measured with 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 in the analog repository’s AI chip, allowing users to perform ‘rock, paper, scissors that can never be won.'”
The company said it hopes the demonstration of the chip prototype will “foster a broader understanding of reservoir computing” and that this will lead to accelerated commercialization of reservoir computing devices for cutting-edge artificial intelligence applications.
The new design builds on TDK’s previous research on neuromorphic devices that attempted to mimic the brain using spintronics.
Instead of tackling heavy computational work, this analog repository AI is designed for fast, low-power handling of time series data, making it perfect for sensing and control at the edge.
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.
Through eeNews Analog
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
