Researchers used oscillations from a microscopic beam of silicon to enable the nonlinear dynamics that allow neural networks to complete tasks ranging from processing image patterns to recognizing words.
As artificial intelligence has become increasingly sophisticated, it has inspired renewed efforts to develop computers whose physical architecture mimics the human brain. One approach, called reservoir computing, allows hardware devices to achieve the higher-dimension calculations required by emerging artificial intelligence. One new device highlights the potential of extremely small mechanical systems to achieve these calculations.
A group of researchers at the Université de Sherbrooke in Québec, Canada, reports the construction of the first reservoir computing device built with a microelectromechanical system (MEMS). Published in the Journal of Applied Physics, from AIP Publishing, the neural network exploits the nonlinear dynamics of a microscale silicon beam to perform its calculations. The group’s work looks to create devices that can act simultaneously as a sensor and a computer using a fraction of the energy a normal computer would use.
The article appears in a special topic section of the journal devoted to “New Physics and Materials for Neuromorphic Computation,” which highlights new developments in physical and materials science research that hold promise for developing the very large-scale, integrated “neuromorphic” systems of tomorrow that will carry computation beyond the limitations of current semiconductors today.
“These kinds of calculations are normally only done in software, and computers can be inefficient,” said Guillaume Dion, an author on the paper. “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, Dion said, including classifying spoken sounds and processing binary patterns with accuracies of 78.2 percent and 99.9 percent respectively.
“This tiny beam of silicon can do very different tasks,” said Julien Sylvestre, another author on the paper. “It’s surprisingly easy to adjust it to make it perform well at recognizing 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.
The Latest on: Reservoir computer
via Google News
The Latest on: Reservoir computer
- Utah’s Water Dilemmaon November 29, 2021 at 12:16 pm
Three pipeline projects in Utah aim to move water dozens or hundreds of miles to high-growth population centers. Utah has some of the highest residential water use in the country, and relatively cheap ...
- Fishing Report: Fishing Regulations changing for season, fishing still good in many waterson November 26, 2021 at 10:23 am
As you will see in your fishing report, fishing regulations have changed for the season. One change I am looking forward to is Indian Creek Reservoir and the surrounding area. I have been in contact ...
- Finding out I have Asperger's showed me that I’m not aloneon November 16, 2021 at 8:51 pm
Nobody else feels like this. I'm on the couch next to my mum. Her shoulder pressed against my side, to allow the computer to view both of us. We're meeting with a psychologist on Skype.
- HIV ‘miracle’ as woman’s body rids itself of deadly diseaseon November 16, 2021 at 1:41 am
A computer illustration showing the HIV virus ... In most patients, new particles are constantly made from a ‘viral reservoir’. During infection, HIV places copies of its genome into the ...
- Feds change Colorado River forecasting methods to reflect climate change. Still 'too rosy'?on November 16, 2021 at 1:00 am
Done with computer models into which historical climate ... “most probable,” “minimum probable” and “maximum probable” reservoir elevations. The most probable are the most important ...
- How SARS-CoV-2 in American deer could alter the course of the global pandemicon November 14, 2021 at 6:49 pm
Scientists have evidence that SARS-CoV-2 spreads explosively in white-tailed deer and that the virus is widespread in this deer population across the United States. Researchers say the findings are ...
- Beauty is in the Eye of the Camera-Holderon November 10, 2021 at 4:09 am
(MENAFN- Zex PR Wire) Singapore, 10 Nov 2021, ZEXPRWIRE , As the sun sets over Singapore, a group of men and women with cameras can be seen by the entrance to MacRitchie Reservoir Park in the ...
- How SARS-CoV-2 in American deer could alter the course of the global pandemicon November 9, 2021 at 3:59 pm
In September of last year, computer models suggested SARS-CoV-2 ... suggests that white-tailed deer could become what's known as a reservoir for SARS-CoV-2. That is, the animals could carry ...
via Bing News