New Artificial Neural Networks To Use Graphene Memristors
Research in the field of traditional computing systems is slowing down, with new types of computing moving to the forefront now.
A team of engineers from Pennsylvania State University (Penn State) in the U.S. has been working on creating a type of computing based on our brain's neural networks' systems all while using the brain's analog nature.
The team has discovered that graphene-based memory resistors show promise for this new computing form.
Their findings were recently published in Nature Communications.
"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," said Saptarshi Das, the team leader and Penn State assistant professor of engineering science and mechanics.
As traditional computing systems become more and more limited, the need for new computing systems arise. For instance, there is now a need for high-speed image processing for self-driving cars. Data is becoming bigger, so different types of computing are now required.
"We are creating artificial neural networks, which seek to emulate the energy and area efficiencies of the brain," explained Thomas Schranghamer, first author of the paper and doctoral student in the Das group.
"The brain is so compact it can fit on top of your shoulders, whereas a modern supercomputer takes up space the size of two or three tennis courts," he continued.
The team is building artificial neural networks that work like the synapses in our brain, which connect the brain's neurons and can be reconfigured. The team's artificial neural networks can be reconfigured by placing a brief electric field to a sheet of graphene, reported Physics World.
"What we have shown is that we can control a large number of memory states with precision using simple graphene field effect transistors," said Das.
The team can, in fact, create 16 different possible memory states and believes its technology can be made on a commercial scale.