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.
Receive an email update when we add a new RESERVOIR COMPUTER article.
The Latest on: Reservoir computer
via Google News
The Latest on: Reservoir computer
- Water's Edge colonial offered in Clinton Twp. on November 13, 2018 at 8:03 am
A private study makes a perfect den or computer room. Completing this level are well-appointed ... Sited on a premium lot backing up Spruce Run Reservoir, the grounds are professionaly landscaped and ... […]
- Lucd Announces Ground Breaking Advancements in Reservoir Computing on November 12, 2018 at 10:20 am
Demonstrating scalability of large-scale Reservoir Computing models is a game changer in the field," noted Chris Carothers, Ph.D., Director, Center for Computational Innovations and Professor, Compute... […]
- Some of Earth’s water came from a stream of hydrogen long ago on November 12, 2018 at 8:18 am
But, says a team of researchers, some of the H 2 O that covers much of our planet’s surface was once something very different: A reservoir of hydrogen in ... To find out, the team created a computer m... […]
- The Role of Semiconductors in Quantum Computing on November 12, 2018 at 12:51 am
There are a few requirements that are necessary for a quantum computer to be efficient ... be able to control the interactions between the spin and external reservoir and have the ability to perform o... […]
- About 200 gather for Marine birthday breakfast on November 10, 2018 at 6:05 pm
He accompanied his talk with computer-screen images of his own war-time experiences ... He showed photos of the sculpture’s eight panels, and called the battle of Chosin Reservoir during the Korean Wa... […]
- Global Exploration & Production (E&P) Software Market Projected to Touch US$14,149.6 mn by 2025 on November 9, 2018 at 10:01 pm
The market has further been classified into several E&P software types such as risk management mapping, seismic amplitude analysis, portfolio aggregation, performance tracking, navigation system, reso... […]
- BEST COMPUTER SCIENCE PROJECT TOPICS IN NIGERIA on October 24, 2018 at 3:02 am
A reservoir of standard computer science project topics and research materials has been made available for interested student at Codemint.com. Codemint has in stock certified project and seminar topic ... […]
- New reservoir computer marks first-ever microelectromechanical neural network application on October 16, 2018 at 4:23 pm
A group of researchers reports the construction of the first reservoir computing device built with a microelectromechanical system. The neural network exploits the nonlinear dynamics of a microscale s... […]
- New reservoir computer marks first-ever microelectromechanical neural network application on October 16, 2018 at 8:08 am
A single silicon beam (red), along with its drive (yellow) and readout (green and blue) electrodes, implements a MEMS capable of nontrivial computations. Credit: Guillaume Dion As artificial intellige... […]
via Bing News