Study unveils portentous advancements made in neuromorphic computing
Appearing online in Nature Communications, a new study details the significant advancements made by a team of researchers at the University of Massachusetts Amherst in the conceptual field of neuromorphic computing.
The conceptual field involves the use of machines to emulate the neural structure and operation of the human brain. Although previous research has devoted to understanding the concepts of neuromorphic computing, the field still remains widely unexplored.
In the new study, researchers unveiled how to construct a neuromorphic memristor, or memory transistor device, using protein nanowires.
Memristors would essentially function similarly to actual brain synapses, inducing a lower voltage in the simulation to accurately carry signals between neurons.
In an actual brain, the sending of signals known as action potentials between neurons occurs near 80 millivolts, whereas typical computing equipment operates at over 1 volt. Researchers say the new experiments confirm that memristors could now reach neurological voltages, similar to a human brain.
“This is the first time that a device can function at the same voltage level as the brain. People probably didn’t even dare to hope that we could create a device that is as power-efficient as the biological counterparts in a brain, but now we have realistic evidence of ultra-low power computing capabilities,” said Jun Yao, co-author of the study.
“It’s a concept breakthrough and we think it’s going to cause a lot of exploration in electronics that work in the biological voltage regime.”