from the maybe-this-will-help-them-sell-their-chip-business dept.
A new kind of computer chip, unveiled by IBM today, takes design cues from the wrinkled outer layer of the human brain. Though it is no match for a conventional microprocessor at crunching numbers, the chip consumes significantly less power, and is vastly better suited to processing images, sound, and other sensory data.
IBM's SyNapse chip processes information using a network of just over one million "neurons," which communicate with one another using electrical spikes-as actual neurons do. The chip uses the same basic components as today's commercial chips-silicon transistors. But its transistors are configured to mimic the behaviour of both neurons and the connections-synapses-between them.
Related Stories
A new brain-inspired architecture could improve how computers handle data and advance AI
IBM researchers are developing a new computer architecture, better equipped to handle increased data loads from artificial intelligence. Their designs draw on concepts from the human brain and significantly outperform conventional computers in comparative studies. They report on their recent findings in the Journal of Applied Physics, from AIP Publishing.
[...] The IBM team drew on three different levels of inspiration from the brain. The first level exploits a memory device's state dynamics to perform computational tasks in the memory itself, similar to how the brain's memory and processing are co-located. The second level draws on the brain's synaptic network structures as inspiration for arrays of phase change memory (PCM) devices to accelerate training for deep neural networks. Lastly, the dynamic and stochastic nature of neurons and synapses inspired the team to create a powerful computational substrate for spiking neural networks.
[...] Last year, they ran an unsupervised machine learning algorithm on a conventional computer and a prototype computational memory platform based on phase change memory devices. "We could achieve 200 times faster performance in the phase change memory computing systems as opposed to conventional computing systems." Sebastian said. "We always knew they would be efficient, but we didn't expect them to outperform by this much." The team continues to build prototype chips and systems based on brain-inspired concepts.
Biosensor response from target molecules with inhomogeneous charge localization (DOI: 10.1063/1.5036538) (DX)
Previously: IBM Chip Processes Data Similar to the Way Your Brain Does
IBM Builds New Form of Memory that Could Advance Brain-Inspired Computers
Simulating Neuromorphic Supercomputing Designs
The Second Coming of Neuromorphic Computing
Novel Synaptic Architecture for Brain Inspired Computing
(Score: 3, Interesting) by bugamn on Sunday August 10 2014, @01:28AM
From the article, it seems like this is a chip designed to implement directly neural networks, and in that they can work faster and consuming less power. Now let's see if they will be used.
(Score: 3, Funny) by jasassin on Sunday August 10 2014, @01:43AM
But its transistors are configured to mimic the behaviour of both neurons and the connections-synapses-between them.
I can just see the newegg reviews on this chip:
1 egg
Pros: none
Cons: senile out of box
Other thoughts: after installing this chip all my computer would do is drool and piss and shit itself
1 egg
Pros: sometimes its nice.
Cons: sometimes its mad... Mean mad.
Other thoughts: This bi polar CPU is really getting to me. Do not recommend. Stay away.
jasassin@gmail.com GPG Key ID: 0xE6462C68A9A3DB5A
(Score: 3, Funny) by Marand on Sunday August 10 2014, @10:54AM
4 egg
pros: bloody awesome when it works
cons: needs giant cup of coffee in the morning before it will start working, keeps demanding cheetos and mountain dew during late-night coding sessions.
other thoughts: joined my D&D group on weekends; makes an excellent DM.
(Score: 3, Informative) by kaszz on Sunday August 10 2014, @01:52AM
This might be related to these projects:
* Blue brain project [wikipedia.org], 2005 Switzerland
* Human brain project [wikipedia.org], 2013 European Union
* BRAIN Initiative [wikipedia.org], 2013 USA
In strong AI, the lunch eats you! ;)
Humans are perhaps to stupid collectively to comprehend the inherent risk with these projects.
(Score: 1) by Subsentient on Sunday August 10 2014, @01:55AM
I can see the danger clearly. Terminator meets Borg, anyone?
"It is no measure of health to be well adjusted to a profoundly sick society." -Jiddu Krishnamurti
(Score: 3, Interesting) by kaszz on Sunday August 10 2014, @02:20AM
Rather military leadership would be outsmarted and sidelined while their own AI does what it deems necessary for whatever goal it has if any. It will probably be something along this lines but not as we have imagine it. The future has a tendency to keep themes and metaphors but actual events usually happens in other ways than imagined.
Long ago. Futurists imagined that orchestras would do live performances and the music would be distributed by means of very long tubes into living quarters. Well think about it. What did happen and what means were used? ;)
We have also come a long way from Baird scanning disc television but the principles from 1924 still remains. Raster, serialization, signal conditioning etc.
(Score: 1) by DECbot on Sunday August 10 2014, @03:43AM
More like the borg meets twitter.
cats~$ sudo chown -R us /home/base
(Score: 3, Funny) by Tork on Sunday August 10 2014, @02:19AM
🏳️🌈 Proud Ally 🏳️🌈
(Score: 2) by SlimmPickens on Sunday August 10 2014, @03:14AM
I did enjoy reading that.
(Score: 3, Funny) by maxwell demon on Sunday August 10 2014, @05:01AM
The chip won't have problems with that. However, give it an image of a pretty silicon chip ...
The Tao of math: The numbers you can count are not the real numbers.
(Score: 2) by kaszz on Monday August 11 2014, @01:08AM
Oh my silicon!, your wafer pattern is so squarely and low capacitance.. I just feel we have to etch some new transistor masks together..!!
;-)
(Score: 1) by Camembert on Monday August 11 2014, @10:06AM
It would be interesting to tinker with such a chip in a small computer a la raspberry pi. Probably not possible for that price of course. Does IBM plan development boards woth it?