Neuromorphic computing, simulating human brain

#1
This is the first time I've heard of this.

Professor Jennifer Hasler displays a field programmable analog array (FPAA) board that includes an integrated circuit with biological-based neuron structures for power-efficient calculation. Hasler’s research indicates that this type of board, which is programmable but has low power requirements, could play an important role in advancing neuromorphic computing. Credit: Rob Felt

(Phys.org) —In the field of neuromorphic engineering, researchers study computing techniques that could someday mimic human cognition. Electrical engineers at the Georgia Institute of Technology recently published a "roadmap" that details innovative analog-based techniques that could make it possible to build a practical neuromorphic computer.

A core technological hurdle in this field involves the electrical power requirements of computing hardware. Although a human brain functions on a mere 20 watts of electrical energy, a digital computer that could approximate human cognitive abilities would require tens of thousands of integrated circuits (chips) and a hundred thousand watts of electricity or more – levels that exceed practical limits.

The Georgia Tech roadmap proposes a solution based on analog computing techniques, which require far less electrical power than traditional digital computing. The more efficient analog approach would help solve the daunting cooling and cost problems that presently make digital neuromorphic hardware systems impractical.

"To simulate the human brain, the eventual goal would be large-scale neuromorphic systems that could offer a great deal of computational power, robustness and performance," said Jennifer Hasler, a professor in the Georgia Tech School of Electrical and Computer Engineering (ECE), who is a pioneer in using analog techniques for neuromorphic computing. "A configurable analog-digital system can be expected to have a power efficiency improvement of up to 10,000 times compared to an all-digita



Read more at: http://phys.org/news/2014-04-neuromorphic-roadmap-envisions-analog-path.html#jCp

Chips that mimic the brain
No computer works as efficiently as the human brain – so much so that building an artificial brain is the goal of many scientists. Neuroinformatics researchers from the University of Zurich and ETH Zurich have now made a breakthrough in this direction by understanding how to configure so-called neuromorphic chips to imitate the brain's information processing abilities in real-time. They demonstrated this by building an artificial sensory processing system that exhibits cognitive abilities.
http://medicalxpress.com/news/2013-07-chips-mimic-brain.html#inlRlv
 
#2
I'm not sure how amazing of a discovery this really is. From what I understand it sounds like they took an FPGA unit and gave it a schematic file for artificial neurons, and then called it a success.

The gentleman who wrote about "NSA At Home" covered the ridiculously performant nature of these kinds of devices a few years ago, though the cost to actually obtain an FPGA currently outstrips the benefits for most uses. Maybe that will change with graphene being mass producable?
 
S

Sciborg_S_Patel

#3
I'm not sure how amazing of a discovery this really is. From what I understand it sounds like they took an FPGA unit and gave it a schematic file for artificial neurons, and then called it a success.
Seems like part of the Easy Problem that Chalmers talks about in Facing Up to the Problem of Consciousness. (Relevant thread here, so as not to derail this one about faster computers.)
 
Top