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
- Killer coronavirus could have come from BATS – like SARS and Ebola viruses before iton January 22, 2020 at 1:13 am
It was thought to have been spread from bats to civet cats at an animal reservoir before being transmitted to humans in the Guangdong ... They estimated how the viral strain would interact with cells ...
- Crude oil and natural gas Marketon January 20, 2020 at 7:53 pm
Digital oil fields integrate advanced computer code, hardware ... and 3D seismic imaging and reservoir modelling. Oilfields conversion facilitates economical utilization of human resources and ...
- How Solar Panels Help Green Trainson January 20, 2020 at 12:13 pm
The reservoir contains about 20 to 25 gallons of friction modifier ... And inside here we have a battery and we also have the computer which counts the wheels and controls the application rate. We can ...
- Computer Modelling Group’s (CMG) Sector Perform Rating Reaffirmed at Royal Bank of Canadaon January 19, 2020 at 10:23 pm
Computer Modelling Group Ltd., a computer software technology company, develops and licenses reservoir simulation software in Canada. The company offers CMOST AI, an intelligent optimization and ...
- Too much rain: Reservoir officials attempt to mitigate flooding from Pearl Riveron January 16, 2020 at 12:01 pm
With record rains inundating parts of Mississippi over the last week and more rain falling, Ross Barnett Reservoir officials announced a plan to protect homes and businesses in Jackson from the rising ...
- Passive water ascent in a tall, scalable synthetic treeon January 14, 2020 at 2:41 am
The secondary reservoir (i.e. filled plastic container) was placed on top of a mass balance (Scout Series, Ohaus) interfaced with a computer. The reservoir was sealed with a rubber lid, such that ...
- Survey studies sediments in Malampuzha damon January 13, 2020 at 9:56 am
The data collected through DGPS and echosounder will be analysed using a computer software to get the exact volume of water. Ms. Shini said the winds in the reservoir area were affecting the movement ...
- In search of the salamander: EBMUD biologist nurtures elusive specieson January 13, 2020 at 8:10 am
James Jones pulls onto the gravel edge of a road near Camanche Reservoir and clicks off the engine of his truck ... Back at his office in Lodi, he will add this photo to a gallery of specimens on a ...
- Digital Oilfield Market 2020 Opportunity Analysis and Industry Forecast by 2025- MREon January 12, 2020 at 6:59 pm
New York, January 13, 2020: The Digital Oilfield Market is segmented on the lines of its process, application, solution and regional. Based on process is segmented into Reservoir Optimization, ...
via Bing News