Stanford scientistshave generated a computer hardware organisation based on the human wit that is able of simulating , in real - time , a million neurons with billions of synaptic connection using only a similar amount of power to what is required to run a tablet computer . The results have been published inProceedings of the IEEE .
Generating good example that can copy genius activity is guileful business concern . Personal computer simulations of the pallium of a shiner are approximately9,000 times slowerthan the real thing and eat around 40,000 times more world power . The Human Brain Project desires to simulate a human - exfoliation cortex , but as it stands it ’s predicted to require around as much powerfulness as 250,000 households !
In this study scientist generated system that they are callingNeurogrid , which is be of 16 “ Neurocore ” chips desegregate together on a circuit board . Each Neurocore can support65,536neurons , stand for over a million neuron can be simulated altogether with their billions of synaptic connections in real - time . Rather imposingly it also only involve 3 James Watt to run ; a PC simulating twice as many neurons practice several hundred W and is around 9,000 time slower than genuine - fourth dimension .
This new system could open up raw door in robotics and brain modeling , and the scientist trust that it may eventually be transitioned into an affordable system which can be widely used by research worker without demand extensive noesis of the workings of the brain .
regrettably a drawback at the mo is the high cost involve in developing ; each Neurogrid cost around $ 40,000 . However , the squad are first to accommodate that they are currently using 15 - year - old technologies . If they interchange to more modern fictionalization processes then they should be able to cut price to around only $ 400 . Not only that , it would also tolerate them to increase the memory of each Neurocore by two orders of magnitude .
In malice of its efficiency when compared with other arrangement , it still pales in equivalence to the noteworthy workings of the human brain . Running a web of 80,000 times as many neurons , it only gobbles up around three times as much power as Neurogrid .
The scientist have big future visions for this system ; Neurogrid ’s unbelievable efficiency and fastness may at some stage beappliedto drive prosthetic limbs in a manner comparable to our own actions . They hope that it could finally be imbed into the brain of a paralyzed person in lodge to move as a translator , allowing the executing of trend of prosthetic limbs .
To observe out more , check out this YouTube video recording from Stanford University :
