March 22, 2005 5:23 PM PST

IBM computing algorithm thinks like an animal

IBM has devised a way to let computers think like vertebrates.

Charles Peck and James Kozloski of IBM's Biometaphorical Computing team say they have created a mathematical model that mimics the behavior of neocortal minicolumns, thin strands of tissue that aggregate impulses from neurons. Further research could one day lead to robots that can "see" like humans and/or make appropriate decisions when bombarded with sensory information.

A research paper on the model is expected to come out this week.

The brain consists of roughly 28 billion cells, Peck explained. The 200 million minicolumns essentially gather sensory data and organize it for higher parts of the brain. The minicolumns also communicate with each other through interconnections. Minicolumns are roughly 1/20 of a millimeter in diameter and extend through the cortex.

The mathematical model created at IBM simulates the behavior of 500,000 minicolumns connected by 400 million connections. With it, "we were able to demonstrate self-organization" and behavior similar to that seen in the real world, Peck said.

"What we are trying to do is study the brain at the highest level of abstraction without masking the underlying function," he said.

In a test outlined in the upcoming paper, the system was able to solve a pattern recognition problem that will cause errors on ordinary computers.

Ideally, the algorithm could one day help scientists more fully understand the underlying processing that takes place when people see things. In a nutshell, an image is received, decomposed into color, shape, texture and other attributes and then reassembled, prompting the animal to change its behavior. Not all parts of the process are fully understood, Peck said.

Over the past two years, researchers have increasingly looked toward nature as a model to emulate. Some companies, such as Cambrios, are trying to develop new compounds by exploiting proteins secreted by biological viruses. PalmOne founder Jeff Hawkins, meanwhile, is creating a company that will sell systems that use the same thought processes as the human brain. Intel co-founder Gordon Moore recently said that computers won't likely be able to think like humans unless they are redesigned.

Brains typically think by making predictions about future events by looking at a vast array of past experiences, Hawkins said in a speech Monday at an event unrelated to IBM. Hawkins showed off a prototype application that can recognize shapes it has "seen" in the past.

IBM is presenting the paper at the International Conference on Adaptive and Natural Computing Algorithms in Coimbra, Portugal.

4 comments

Join the conversation!
Add your comment
can you say god?
this, indeed, may be the first step toward replacing humanity with a new "creature" that can expedite "evolution" of its own volition, far more rapidly than darwin's theory has allowed for.
Posted by mortis9 (370 comments )
Reply Link Flag
Are invertebrates not animals?!
This article was interesting. However, why does the secondary
title state that, "IBM has devised a way to let computers think
like vertebrates" after saying, "IBM computing algorithm thinks
like an animal"? Are invertebrates not animals? I would vebture
to say that many, many invertebrates' brains function in the
same way that this algorithm is attempting to replicate. Why
mention vertebrates specifically, as if equating animals only to
vertebrates? I don't have a PhD in neurophysiology or zoology,
so if someone can explain how I misunderstood, please let me
know.

Todd
Posted by (1 comment )
Reply Link Flag
Economic System Shift.
A truly intelligent machine would change things dramatically. If companies can buy robots for USD $50,000 that demand no salary, only energy and maintenance, and that are two or three times more productive (not to mention that hooking to the Internet would be the only thing they would need to quickly learn new things), every company will fire its employees and hire robots to manufacture products that nobody will be able to buy for not having money as the result of no having jobs. This would create chaos. That means the system WILL HAVE TO CHANGE. I imagine a new kind of system, that for lack of a better word we may call Socialism, in which people get paid simply for existing. Of course, the more education the higher the pay, so everybody will turn to schools to get a better education. Seeing people with two or three Ph.D.s may not be rare in such future.
Posted by (2 comments )
Reply Link Flag
Knowledge Circles.
An intelligent machine would mean such machine will create a more intelligent machine, and so on, until machines will have knowledge humans would not dare not even in a thousand years. Machines may have their own knowledge circles, having journals in which only machines publish and only machines read about. Humans will be left creating technology at their own pace having their own human journals. Machines will be able to build vehicles no one has even dreamed about, reaching out to explore the solar system and beyond.
Posted by (2 comments )
Reply Link Flag
 

Join the conversation

Add your comment

The posting of advertisements, profanity, or personal attacks is prohibited. Click here to review our Terms of Use.

What's Hot

Discussions

Shared

RSS Feeds

Add headlines from CNET News to your homepage or feedreader.