icon bookmark-bicon bookmarkicon cameraicon checkicon chevron downicon chevron lefticon chevron righticon chevron upicon closeicon v-compressicon downloadicon editicon v-expandicon fbicon fileicon filtericon flag ruicon full chevron downicon full chevron lefticon full chevron righticon full chevron upicon gpicon insicon mailicon moveicon-musicicon mutedicon nomutedicon okicon v-pauseicon v-playicon searchicon shareicon sign inicon sign upicon stepbackicon stepforicon swipe downicon tagicon tagsicon tgicon trashicon twicon vkicon yticon wticon fm
25 Jan, 2018 11:01

‘Brain-like microchip the size of fingernail’ could replace supercomputers – MIT study

‘Brain-like microchip the size of fingernail’ could replace supercomputers – MIT study

Engineers based in Boston are working on a computer chip that could transmit varying levels of information at speeds as fast as a human brain. It’s hoped the development could miniaturize supercomputer technology.

Currently, microchip technology is limited by signals relayed in a binary on and off fashion through electric currents. However, through the design of artificial neurons and synapses, experts at the Massachusetts Institute of Technology (MIT) are hoping to replicate the computing power of a human brain.

Around 100 trillion synapses – neural-transmission channels – enable chemical signals to travel around the brain, allowing for bodily functions such as voluntary movement.

By creating man-made synapses, MIT scientists believe they can control the strength of an electric current as established between human brain neurons. The attempt is detailed in a Nature journal study led by Jeehwan Kim, of MIT’s Research Laboratory of Electronics.

The project would help downsize supercomputer abilities into small neuromorphic digital chips, according to MIT. However, the team of scientists had issues with finding the right conducting material for a synthetic synapse.

“Once you apply some voltage to represent some data with your artificial neuron, you have to erase and be able to write it again in the exact same way,” Kim said in a statement. He says it’s hard to control and the biggest problem is “nonuniformity of the artificial synapse.”

READ MORE: Diabetes drug tackles effects of Alzheimer’s in mice – study

“Ultimately we want a chip as big as a fingernail to replace one big supercomputer,” Kim added. “This opens a stepping stone to produce real artificial hardware.”

Think your friends would be interested? Share this story!

Podcasts
0:00
28:20
0:00
27:33