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
- Scuttlebiz: The 32 words that changed Augusta foreveron October 8, 2020 at 11:03 am
Also high on the list would be the 1954 completion of the Clarks Hill Dam, which simultaneously ended decades of periodic floods and created the largest man-made reservoir east of ... Glover, 33, a ...
- Middletown Man Watches Bald Eagle Swoop Down His Suburban Streeton October 5, 2020 at 11:47 am
A 36-year-old Middletown man watched in amazement as a bald eagle landed on his sidewalk Monday morning to pick up a dead squirrel.
- Gun wielding thugs rob Reservoir Hills familyon September 28, 2020 at 4:05 am
A 67-year-old woman, her daughter and grandson were at home when three men brandishing firearms and wearing balaclavas entered the house through an unlocked kitchen door.
- Computer Modelling Group (TSE:CMG) Shares Cross Above 200 Day Moving Average of $4.85on September 24, 2020 at 11:45 pm
Computer Modelling Group Ltd. (TSE:CMG)’s share price passed above its 200-day moving average during trading on Thursday . The stock has a 200-day moving average of $4.85 and traded as high as $5.09.
- The coronavirus pandemic and the future of oilon September 21, 2020 at 1:49 pm
The latest oil and gas news, dedicated to all things oil and gas: people, technologies, transactions, trends, and macro-economic analysis that impact commodity prices.
- XSPC Raystorm 750 RX360 Liquid Cooling Kit Reviewon September 17, 2020 at 8:50 pm
The reservoir is made of high quality acrylic ... With a few years of abusing computer parts, he decided to take his chances and try to get a review job. As an avid overclocker, Chad is always ...
- Horizontal Wellon September 17, 2020 at 5:00 pm
Operators use it to retrieve oil and natural gas in situations in which the shape of the reservoir is abnormal ... become a more popular technique as computer-aided technology has become more ...
- There is a giant liquid-cooling reservoir on the back of this open-frame caseon September 14, 2020 at 6:48 am
Over the years, Thermaltake has released several iterations of its open-frame computer case ... DistroCase 350P is basically a giant channeled reservoir (it holds around 800ml of coolant) with ...
- Worldwide Digital Oilfield Industry to 2025 - Featuring Emerson, Rockwell & Siemens Among Otherson September 11, 2020 at 4:24 am
DUBLIN, Sept. 11, 2020 /PRNewswire/ -- The "Digital Oilfield Market by Solutions (Hardware, Software & Service, and Data Storage Solutions), Processes (Reservoir, Production, and Drilling ...
via Bing News