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
[google_news title=”” keyword=”reservoir computer” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Reservoir computer
- Sinkholes in Amistad Dam threaten international border water reservoiron December 6, 2023 at 3:58 pm
The largest international dam on the Texas/Mexico border has sinkholes and is unsafe and has been in need of costly repairs for decades, the U.S. International Boundary and Water Commission head ...
- Definition of 'reservoir'on December 2, 2023 at 4:00 pm
A reservoir is a lake that is used for storing water before it is supplied to people. 2. countable noun A reservoir of something is a large quantity of it that is available for use when needed. ...the ...
- The Courseon December 2, 2023 at 2:34 am
The course is 5000m (5k) long. This has been accurately measured by us with a professional measuring wheel. The course is at Edgbaston Reservoir, Birmingham. The course is run on a mixture of tarmac ...
- Site C returns to original start of fall 2024 for reservoir fillingon November 29, 2023 at 3:59 pm
FORT ST. JOHN, B.C. — The filling of the Site C reservoir will begin on schedule in the fall of 2024 instead of an early start this fall. The dam was initially scheduled to be filled in 2024 ...
- Computer simulation of shoreline erosion on a fetch-limited prairie reservoir (Lake Diefenbaker, 1967-1980)on November 28, 2023 at 11:17 am
In order to determine if computer simulation techniques are of any use in estimating ... The study found that enough wave energy is generated on the reservoir to remove all eroded material from the ...
- Quantum Computing Inc. Achieves Milestone with First Sale of Reservoir Computer and Quantum Random Number Generatoron October 31, 2023 at 6:00 am
The Company has secured multiple hardware sales of its state-of-the-art Reservoir Computer and Quantum Random Number Generator to Assured Cyber Protection Ltd and AI firm millionways, kicking off the ...
- Quantum Computing Inc. Achieves Milestone with First Sale of Reservoir Computer and Quantum Random Number Generatoron October 31, 2023 at 5:00 am
The Company has secured multiple hardware sales of its state-of-the-art Reservoir Computer and Quantum Random Number Generator to Assured Cyber Protection Ltd and AI firm millionways, kicking off ...
- Quantum Computing Inc. Achieves Milestone with First Sale of Reservoir Computer and Quantum Random Number Generatoron October 30, 2023 at 5:00 pm
Quantum Computing Inc.'s partners Assured Cyber Protection Ltd and millionways order Reservoir Computers and Quantum Random Number Generator to enhance their AI capabilities.
via Bing News