Modelled on the human brain, The Neurogrid chip can simulate 1 million neurons and billions of synapses or brain connections.
That is a vast improvement over previous brain simulations but still only a fraction of the roughly 80 billion neurons in the human brain, researchers said.
“From a pure energy perspective, the brain is hard to match. Not only are personal computers slower, they take 40,000 times more power than the brain to run,” said Kwabena Boahen, a bio-engineer at Stanford University whose brainchild the chip is.
Neurogrid has of 16 custom-designed Neurocore chips in a device the size of an iPad.
This can open up windows into understanding the human brain and developing new forms of computing patterned after brain circuits.
Now, the scientists are working to adapt Neurogrid for controlling prosthetic limbs for paralysed people.
The chip can translate brain signals into movements of the limb, without overheating the brain, media reports said.