Researchers build human brain-mimicking 'reservoir computing' device

Reservoir computing can achieve the higher-dimension calculations required by emerging AI

A group of researchers at the Université de Sherbrooke in Quebec, Canada, have built what they are calling the first "reservoir computing" device.

Reservoir computing is just one approach where a computer's physical architecture mimics the human brain, enabling hardware devices to achieve the higher-dimension calculations required by emerging artificial intelligence.

Built with a micro-electromechanical system (MEMS), the new device highlights the potential of extremely small mechanical systems to achieve these higher-dimension calculations.

Published in the Journal of Applied Physics, the device's neural network exploits the nonlinear dynamics of a microscale silicon beam to perform its calculations.

The researchers say the device is an attempt to create a computer that can act simultaneously as a sensor and a computer using a fraction of the energy a normal computer would use.

"These kinds of calculations are normally only done in software, and computers can be inefficient," said Guillaume Dion, one of the authors of the paper.

"Many of the sensors today are built with MEMS, so devices like ours would be an ideal technology to blur the boundary between sensors and computers."

The device relies on the non-linear 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, Dion said, including classifying spoken sounds and processing binary patterns with accuracies of 78.2 per cent and 99.9 per cent, respectively.

"This tiny beam of silicon can do very different tasks," added another author of the paper, Julien Sylvestre. "It's surprisingly easy to adjust it to make it perform well at recognising words."

Sylvestre said he and his colleagues are looking to explore increasingly complicated computations using the silicon beam device, with the hopes of developing small and energy-efficient sensors and robot controllers