Graphene memristors open doors for biomimetic computing IMAGE: JENNIFER M. MCCANN/PENN STATE
As progress in traditional computing slows, new forms of computing are coming to the forefront. At Penn State, a team of engineers is attempting to pioneer a type of computing that mimics the efficiency of the brain’s neural networks while exploiting the brain’s analog nature.
Modern computing is digital, made up of two states, on-off or one and zero. An analog computer, like the brain, has many possible states. It is the difference between flipping a light switch on or off and turning a dimmer switch to varying amounts of lighting.
Neuromorphic or brain-inspired computing has been studied for more than 40 years, according to Saptarshi Das, the team leader and Penn State assistant professor of engineering science and mechanics. What’s new is that as the limits of digital computing have been reached, the need for high-speed image processing, for instance for self-driving cars, has grown. The rise of big data, which requires types of pattern recognition for which the brain architecture is particularly well suited, is another driver in the pursuit of neuromorphic computing.
“We have powerful computers, no doubt about that, the problem is you have to store the memory in one place and do the computing somewhere else,” Das said.
The shuttling of this data from memory to logic and back again takes a lot of energy and slows the speed of computing. In addition, this computer architecture requires a lot of space. If the computation and memory storage could be located in the same space, this bottleneck could be eliminated.
“We are creating artificial neural networks, which seek to emulate the energy and area efficiencies of the brain,” explained Thomas Shranghamer, a doctoral student in the Das group and first author on a paper recently published in Nature Communications. “The brain is so compact it can fit on top of your shoulders, whereas a modern supercomputer takes up a space the size of two or three tennis courts.”
Like synapses connecting the neurons in the brain that can be reconfigured, the artificial neural networks the team is building can be reconfigured by applying a brief electric field to a sheet of graphene, the one-atomic-thick layer of carbon atoms. In this work they show at least 16 possible memory states, as opposed to the two in most oxide-based memristors, or memory resistors.
“What we have shown is that we can control a large number of memory states with precision using simple graphene field effect transistors,” Das said.
The team thinks that ramping up this technology to a commercial scale is feasible. With many of the largest semiconductor companies actively pursuing neuromorphic computing, Das believes they will find this work of interest.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Graphene-based memory resistors
- Graphene Electronics Market 2021 - 2024 | Opportunities, Impressive Growth Rate and Development Analysison January 8, 2021 at 4:16 pm
Global Graphene Electronics Market is estimated to reach $797 million by 2024; growing at a CAGR of 47.6% from 2016 to 2024. Graphene is a two-dimensional carbon allotrope which exhibits properties of ...
- Appear Inc to launch World’s Lightest and First Graphene Battery-powered 5G Smartphoneon January 7, 2021 at 4:16 pm
SAN FRANCISCO, Jan. 07, 2021 (GLOBE NEWSWIRE) -- Appear Inc. announced the launch of the world’s lightest and first graphene battery ... The company is based in San Francisco and also operates ...
- The Unreasonable Effectiveness Of Adhesive Tapeon January 7, 2021 at 4:00 pm
The same goes for vinyl-based insulating tapes ... The mechanical exfoliation of Graphene Researchers have also modified this technique to produce graphene. Graphene is composed of single carbon ...
- Next-Gen Electronic Devices Printed Using Graphene-Based Inkjet Processon January 6, 2021 at 4:01 pm
A team at the University of Nottingham used graphene, a material with high electrical conductivity, in an ink-jet printing process to build up mesh together electronic structures that can perform ...
- Physicists observe competition between magnetic orderson January 5, 2021 at 4:00 pm
They became known to a wider audience when two Russian-British scientists were awarded the Nobel Prize in Physics in 2010 for the discovery of graphene ... new technologies based on such ...
Go deeper with Google Headlines on:
Graphene-based memory resistors
Go deeper with Bing News on:
- Programming tweak helps AI software imitate human visual learningon January 12, 2021 at 6:20 am
Using a novel programming tweak, a pair of neuroscientists have managed to replicate human visual learning in computer-based artificial intelligence.
- IBM Leads in Quantum Computing, Ford in Driverless Car Patentson January 12, 2021 at 3:38 am
Artificial intelligence, quantum computers and autonomous vehicles are among the fastest-growing areas of technology, with American companies often in the lead, according to a new study of U.S.
- Tweaking AI software to function like a human brain improves computer's learning abilityon January 11, 2021 at 9:19 pm
Computer-based artificial intelligence can function more like human intelligence when programmed to use a much faster technique for learning new objects, say two neuroscientists who designed such a ...
- Researcher Pursues Virtual-Reality Therapy to Aid Patients in Recovery from Traumatic Brain Injurieson January 11, 2021 at 11:46 am
A UMass Lowell researcher developing innovative therapies for injured children and teens has received more than $700,000 from the National Institutes of Health to support that work.
- Alibaba DAMO Academy's top 10 trends for 2021, from 'post-quantum-supremacy', to brain computer interfaces, AI R&D acceleration and moreon January 10, 2021 at 5:32 pm
Alibaba's global research initiative has compiled its must-read forecast of the fascinating leading trends that will shape the tech industry in the year ahead. From the application of third-generation ...