AI on a MEMS device blurs sensors, computers
The device is based on a reservoir computing approach, which allows hardware devices to achieve the higher-dimension calculations required by emerging artificial intelligence. It is reportedly the first such device built with a microelectromechanical system (MEMS), in which the neural network exploits the nonlinear dynamics of a microscale silicon beam (red, in the above image) to perform its calculations.
“These kinds of calculations are normally only done in software, and computers can be inefficient,” says Guillaume Dion, an author of a paper on the research. “Many of the sensors today are built with MEMS, so devices like ours would be ideal technology to blur the boundary between sensors and computers.”
The device relies on the nonlinear dynamics of how the silicon beam – at widths 20 times thinner than a human hair – oscillates in space. The results from this oscillation are used to construct a virtual neural network that projects the input signal into the higher dimensional space required for neural network computing.
In demonstrations, the system was able to switch between different common benchmark tasks for neural networks with relative ease, say the researchers, including classifying spoken sounds and processing binary patterns with an accuracy of 78.2% and 99.9% respectively.
“This tiny beam of silicon can do very different tasks,” says Julien Sylvestre, a co-author of the paper. “It’s surprisingly easy to adjust it to make it perform well at recognizing words.”
The researchers say they plan to explore increasingly complicated computations using the silicon beam device. Looking ahead, they hope to be able to develop small and energy-efficient sensors and robot controllers.
For more, see “Reservoir computing with a single delay-coupled non-linear mechanical oscillator.”
Related articles:
IBM: Five innovations that will change our lives within five years
Syntiant, Infineon partnership combines mics with AI
Google brings machine learning to the edge
On-device AI growing fast among smartphones
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
eeNews on Google News
