Purchasing new hardware? Read our latest product comparisons

IBM experimental chips emulate the human brain


August 18, 2011

IBM has unveiled two prototype computer chips that are said to emulate the human brain (Im...

IBM has unveiled two prototype computer chips that are said to emulate the human brain (Image: SyNAPSE)

In April, the University of Southern California made the headlines when it announced that researchers there had created a functioning synthetic synapse circuit using carbon nanotubes. Well, today IBM unveiled a new class of experimental computer chips that are designed to emulate the human brain's abilities for perception, action and cognition. According to the company, "The technology could yield many orders of magnitude less power consumption and space than used in today's computers."

Utilizing advanced algorithms and silicon circuitry, the two prototype "neurosynaptic computing chips" are said to recreate the phenomena that takes place between spiking neurons and synapses in biological systems. The idea is that such chips would be used in "cognitive computers," which would learn through experiences - like the human brain - rather than simply being programmed.

To that end, IBM has joined forces with a number of academic partners, to develop such computers through the Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) project. According to the company, "The goal of SyNAPSE is to create a system that not only analyzes complex information from multiple sensory modalities at once, but also dynamically rewires itself as it interacts with its environment - all while rivaling the brain's compact size and low power usage." Phases 0 through 1 have already been completed, while the Defense Advanced Research Projects Agency (DARPA) has reportedly awarded the project US$21 million in funding for Phase 2.

The two chips themselves contain no biological components. According to the press release, however, both chips do feature 256 artificial neurons, with one core containing 262,144 programmable synapses, and the other containing 65,536 learning synapses. In lab tests, the chips have so far been used to execute simple applications such as navigation, machine vision, pattern recognition, associative memory and classification.

Ultimately, IBM hopes to produce a chip system featuring ten billion neurons and hundred trillion synapses, that would consume one kilowatt of power and have a volume of less than two liters (0.5 U.S. gallons).

"Future applications of computing will increasingly demand functionality that is not efficiently delivered by the traditional architecture," said Dharmendra Modha, project leader for IBM Research. "Imagine traffic lights that can integrate sights, sounds and smells and flag unsafe intersections before disaster happens or imagine cognitive co-processors that turn servers, laptops, tablets, and phones into machines that can interact better with their environments."

Partners in Phase 2 of SyNAPSE include Columbia University, Cornell University, the University of California at Merced, and the University of Wisconsin, Madison.

About the Author
Ben Coxworth An experienced freelance writer, videographer and television producer, Ben's interest in all forms of innovation is particularly fanatical when it comes to human-powered transportation, film-making gear, environmentally-friendly technologies and anything that's designed to go underwater. He lives in Edmonton, Alberta, where he spends a lot of time going over the handlebars of his mountain bike, hanging out in off-leash parks, and wishing the Pacific Ocean wasn't so far away.   All articles by Ben Coxworth

Really? With this type of computational power we are still going to have traffic lights?

Johnson Chad
18th August, 2011 @ 03:31 pm PDT

And imagine it on a bad day when it decides to turn all traffic lights green for the hell of it.

Facebook User
18th August, 2011 @ 05:22 pm PDT

Same old story -- give a computer the ability for rational thought and pretty soon we have another cylon attack.

Don't you remember what happened with SkyNet???

18th August, 2011 @ 05:59 pm PDT

DemonDuck, the good news is that it's mimicking the human brain, so it won't be engaging in rational thought. :-)

18th August, 2011 @ 10:05 pm PDT

Ahhh. Nice that this is an IBM project. It will synergize well with Watson, other AI research, as well as other brain research and brain synthesis research that has been ongoing at IBM for quite some time now.

Regarding how the offspring of this research will help cellphones, etc., better interact with their environment: We'll rue the day when we say, "Really officer? I was speeding? Oh I wasn't aware of that", and our cellphone chirps up and says, "Don't buy it! He knew EXACTLY what he was dong! He went as far as to call you a dumb cop as you pulled him over. I say bust his ass!"

19th August, 2011 @ 12:13 am PDT

I'd love to know how much time they spent just coming-up with the name. "Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE)". Or maybe the new chip came up with it on it's own.

Robert Guimont
19th August, 2011 @ 07:15 am PDT

It's hard to understand why so many negative and sarcastic comments here.

This new chip could advance human civilization by having robots with this chip do all the tedious and dangerous work instead of humans. Or robots with this chip could explore the universe and report back to us so we know which planet is worth traveling to. Many other incredible possibilities.

19th August, 2011 @ 02:08 pm PDT

Ok guys, forreals, we're a long way off from any form of electronics actually gaining any form of intelligence. Calm down.

Danie Clawson
19th August, 2011 @ 09:25 pm PDT

Skynet became self aware (insert date here) and started killing everything.... Anyone know a John Connor?

Raymond Johnson
19th August, 2011 @ 11:59 pm PDT

This could make an android like "Data" possible and the project leader is thinking of better traffic control. I wish I could have been the interviewer. I hope he was joking. If not, IBM needs a new PL.

20th August, 2011 @ 04:47 am PDT

geez robo, I wasn't negative or sarcastic until you pointed out the last of the few jobs out there will be filled by mechanicals. so long truck driving, construction, engineering and so on. Obsolete humans.

21st August, 2011 @ 06:32 am PDT

"DemonDuck, the good news is that it's mimicking the human brain, so it won't be engaging in rational thought. :-)

comment alcalde - August 18, 2011 @ 10:05 pm PDT"

ROFL seriously funny. well played sir

Samantha Renault
21st August, 2011 @ 07:43 am PDT

All good and that but it questions the future for mankind doesn't it. first, robots then humanoids, if used or the better of mankind, yeah I'm all for it! but whats the human cost factor? if this the super chip of the future then why can't it be program to have professional attributes ie A doctor would be really good cause all they seem to ask you is what drugs you need? no blood pressure, no temp check. An Virtual Dr can do more than some of the real ones, atleast it will be minus the travel and waiting time getting even sicker from other peoples germs

Ozi Osman Erdenay
22nd August, 2011 @ 03:45 am PDT

@robo... Seriously? That promise has been heralded since the 1950s and earlier. We still aren't all flying around in flying cars. Nobody on my block has a personal jet-pack that they take to work. I don't have a robot butler. There are no colonies on the moon (or even at the depths of the ocean). Could it "advance human civilization"? Um, probably not. Is it a nano-step in making the world a different place? Maybe. But, uh, let's control the hype.

Roderic Langer
22nd August, 2011 @ 08:49 am PDT

@Roderic Last I checked, there was self-driving cars on the streets and a computer beat its human counter parts on Jeopardy. Yes, hype needs controlled, but further introduction and development of technology like this will be one of the root technological disruptive drivers going forward.

Carlos Felfoldi
22nd August, 2011 @ 01:00 pm PDT

Given 10000 years of human history, what progress humans have made is up for debate. Life on Earth was supposed to have been paradise, but people can't get along with each other. After a 100 years these synapse forms could have humans working for them, because humans can't manage themselves very well, and synapses would do a much better job of it. Hopefully the synapse community will let humans survive. They may keep us around for the entertainment value, but at the core, a synapse is likely to rationalize it would be better all around if humans weren't a factor at all.

23rd August, 2011 @ 09:48 am PDT

"This new chip could advance human civilization by having robots with this chip do all the tedious and dangerous work instead of humans. Or robots with this chip could explore the universe and report back to us so we know which planet is worth traveling to. Many other incredible possibilities." - That's how most "robots become self-aware" apocalyptic plots begin! Then these robots start demanding equal rights and status on par with their human masters, which we of course deny and they declare an all out war on humankind (although most likely we declare it first in the name of human sovereignty) and the rest is history, for humankind that is. :P

Shaun Goh
28th August, 2011 @ 07:51 pm PDT
Post a Comment

Login with your gizmag account:

Or Login with Facebook:

Related Articles
Looking for something? Search our 31,683 articles