News for hackers. Stuff that matters.
Re:IBM to build brain-like computers by bd on Sunday November 23, 2008 @07:58PM (#374299)
"Large-scale neural simulations are difficult for computers because neural models do not map onto the Von Neumann architecture. "

http://www.stanford.edu/group/brainsinsilicon/neurogrid.html

These guys have been doing HW neuro chips for a while. They claim to achieve performance similar to IBM supercomputers for a fraction of the price.

Re:IBM to build brain-like computers by jwilliams on Sunday November 23, 2008 @08:42PM (#374333)
"Large-scale neural simulations are difficult for computers because neural models do not map onto the Von Neumann architecture. "

Maybe they should use the Harvard Architecture?

That's half a joke and half serious - a lot of DSP-type applications still use Harvard Architecture.

(ps. One of my favourite textbooks is "Computer Architecture, A Quantative Approach" by Hennessey and Patterson).

Re:IBM to build brain-like computers by timtrueman on Sunday November 23, 2008 @08:18PM (#374318)
"Large-scale neural simulations are difficult for computers because neural models do not map onto the Von Neumann architecture."

I'm not sure I buy that. I can understand if speed is a big deal but I just can't imagine neural models do not map onto current computers. I'd like to see an example proving that sentence.

Re:IBM to build brain-like computers by debt on Sunday November 23, 2008 @08:47PM (#374339)
If the brain operated on the Von Neumann architecture, your thoughts would be processed tremendously slow while expending an enormous amount of energy.

Perhaps the long lost ancestors of the human had brains operating on this principle, but simply couldn't store enough energy to survive.

The brain fires off multiple synapses in multiple places in the brain at different times. If the brain worked like a Von Neumann machine, it could only fire one synapse at one place in the brain at one particular point in time.

The brain executes things in parallel while the Von Neumann is sequential. The brain is incredibly more efficient then the Von Neumann machine I'm using to type this comment on.

Also, why do you not buy this assessment?

Re:IBM to build brain-like computers by timtrueman on Sunday November 23, 2008 @09:14PM (#374359)
So basically you guys are saying it's way faster, but not that it's not technically impossible to do in software on normal computers. I'm just not sure it's NOT cheaper and faster to prototype this stuff in software and then build it in hardware to make it faster once they figure it out. Prototyping in hardware seems slower and more expensive to me...

And FYI I am familiar with neural networks (and artificial neural networks, I've written a few) and I understand it's massively parallel and that neural networks the size of the human brain cannot be simulated on today's hardware but that's not the goal stated in this article. It just sounds like a bunch of guys that are really into hardware and so that's how they're going to do it, and there's nothing wrong with that. I just wanted to know if it's something that that isn't technically possible in software.

Re:IBM to build brain-like computers by jimbokun on Sunday November 23, 2008 @11:04PM (#374441)
To me, it sounds like a bunch of guys who wrote a grant proposal general enough that they can do almost whatever they want after they get the money and still be within the scope of the proposal.
Re:IBM to build brain-like computers by debt on Monday November 24, 2008 @12:24AM (#374481)
There are five universities across many disciplines that are working on this very challenging project. To me, it sounds like you didn't read the article.
Re:IBM to build brain-like computers by jimbokun on Monday November 24, 2008 @10:17AM (#374909)
I think you make my point for me. :)
Re:IBM to build brain-like computers by debt on Monday November 24, 2008 @12:42AM (#374493)
We can't emulate complex brain models on a computer because we don't have the power. We shouldn't because it's incredible inefficient.

IBM proposes finding a hardware model or some material that can be used to properly mimic synapses in the brain. The academic term for this would be neuromorphic engineering.

Re:IBM to build brain-like computers by bd on Sunday November 23, 2008 @09:00PM (#374346)
They use analog building blocks, not digital ones:

"Mead succeeded in mimicking ion-flow across a neuron's membrane with electron-flow through a transistor's channel.

This should not have come as a surprise: the same physical forces are at work in both cases!

A silicon neuron is an analog electronic circuit of transistors that mimic a real neuron's repertoire of ion-channels.

Instead of designing different electronic circuits to emulate each of a wide variety of ion-selective protein pores that stud neurons' membranes, as Mead did in his silicon retina, we came up with a versatile silicon model."

http://www.stanford.edu/group/brainsinsilicon/about.html

Re:IBM to build brain-like computers by timtrueman on Sunday November 23, 2008 @09:16PM (#374362)
And analog circuits cannot be built/modeled in software?
Re:IBM to build brain-like computers by debt on Monday November 24, 2008 @12:32AM (#374484)
It's possible, but requires a massive supercomputer to do any reasonable calculations.

Neuromorphic chips provide a way to minimize both the time and energy used in calculation by having physical chips act as synapses.