Tech giants keep on manufacturing PC chips with exceptional handling power, taking compact AI gadgets to a more elevated level, but would it be able to ever supplant human brain?
All things considered, the human brain has billions of neurons and trillions of neurotransmitters, empowering it to recollect the reality, perceive designs, transmit instructions to different parts of the human body and learn new things at an extraordinary speed. Its handling force might be unbeatable but researchers have endeavoured to make PC chips that work like the human brain, which could make them as powerful as supercomputers.
A group of researchers drove by Jeehwan Kim, an educator at Massachusetts Institute of Technology (MIT), has outlined neuromorphic chips that work in a simple mold like neurons in human brain. It can “efficiently process millions of streams of parallel computations that are currently only possible with large banks of supercomputers,” as indicated by MIT site.
The researchers likewise planned an “artificial synapse that can precisely control the strength of an electric current flowing across it, similar to the way ions flow between neurons.” However, it was difficult to control the stream of particles as exchanging mediums made of indistinct materials encourages particles to move in boundless ways.
“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,” said Kim. “But in an amorphous solid, when you write again, the ions go in different directions because there are lots of defects. This stream is changing, and it’s hard to control. That’s the biggest problem – nonuniformity of the artificial synapse.”
As per the report by MIT, the group of researchers discovered while testing the execution of their neural network hardware that it “recognized handwritten samples 95 percent of the time, compared to the 97 percent accuracy of existing software algorithms.” They trust the innovation will in the end help in building compact chips that can do errands of huge supercomputers.
“Ultimately we want a chip as big as a fingernail to replace one big supercomputer,” said Kim. “This opens a stepping stone to produce real artificial hardware.”