IBM claims step forward in human-like software
COMPUTERS, like humans, can learn. But when Google tries to fill in your search box based only on a few keystrokes, or your iPhone predicts words as you type a text message, it is only a narrow mimicry of the human brain's potential.
The challenge in training a computer to behave like a human brain is technological and physiological, testing the limits of computer and brain science. But IBM researchers say they have made a key step toward combining the two worlds.
The company announced yesterday it has built two prototype chips it says can process data more comparable to the way humans digest information than the chips that now power PCs and supercomputers.
The chips represent a significant milestone in a six-year project involving 100 researchers and some US$41million in funding from the US government's Defense Advanced Research Projects Agency. IBM has also committed an undisclosed amount of money.
The prototypes offer further evidence of the growing importance of "parallel processing," or computers conducting multiple tasks simultaneously. That is important for rendering graphics and crunching large amounts of data.
Real products
The uses of the IBM chips so far are prosaic, such as steering a simulated car through a maze, or playing Pong. It may be a decade or longer before the chips make their way out of the lab and into real products.
But what is important is not what the chips are doing, but how they are doing it, according to Giulio Tononi, a professor of psychiatry at the University of Wisconsin at Madison, who worked with IBM on the project.
The chip's ability to adapt to types of information it was not specifically programmed to expect is a key feature.
Tononi said: "There is a lot of work to do, but the most important thing is usually the first step, and this is not one step, it is a few steps."
Technologists have long imagined computers that learn like humans. Google's and iPhone servers can be programmed to predict certain behavior based on past events. But the techniques being explored by IBM and other companies and university research labs around "cognitive computing" could lead to chips better able to adapt to unexpected information.
IBM's interest in the chips lies in their potential to help process real-world signals such as temperature, sound and motion and make sense of them for computers.
IBM, based in Armonk, New York, is a leader in the movement to link physical infrastructure, such as power plants or traffic lights, to information technology, such as servers and software that help regulate their functions. Such projects can be made more efficient with tools to monitor the myriad analog signals present in those environments.
Dharmendra Modha, project leader for IBM Research, said the new chips have parts that behave like digital "neurons" and "synapses" that make them different than other chips. Each "core," or processing engine, has computing, communication and memory functions.
"You have to throw out virtually everything we know about how these chips are designed," he said. "The key difference really is the memory and the processor are very closely brought together. There is a massive, massive amount of parallelism."
The project is part of the same research that led to IBM's announcement in 2009 that it had simulated a cat's cerebral cortex, the thinking part of the brain, using a huge supercomputer. Using progressively bigger supercomputers, IBM had previously simulated 40 percent of a mouse's brain in 2006, a rat's full brain in 2007, and 1 percent of a human's cerebral cortex in 2009.
A computer with the power of the human brain is not yet near. But Modha said the latest development is an important step.
"It really changes the perspective from 'What if?' to 'What now?'" Modha said. "Today we proved it was possible. There have been many skeptics, and there will be more, but this completes in a certain sense our first round of innovation."
The challenge in training a computer to behave like a human brain is technological and physiological, testing the limits of computer and brain science. But IBM researchers say they have made a key step toward combining the two worlds.
The company announced yesterday it has built two prototype chips it says can process data more comparable to the way humans digest information than the chips that now power PCs and supercomputers.
The chips represent a significant milestone in a six-year project involving 100 researchers and some US$41million in funding from the US government's Defense Advanced Research Projects Agency. IBM has also committed an undisclosed amount of money.
The prototypes offer further evidence of the growing importance of "parallel processing," or computers conducting multiple tasks simultaneously. That is important for rendering graphics and crunching large amounts of data.
Real products
The uses of the IBM chips so far are prosaic, such as steering a simulated car through a maze, or playing Pong. It may be a decade or longer before the chips make their way out of the lab and into real products.
But what is important is not what the chips are doing, but how they are doing it, according to Giulio Tononi, a professor of psychiatry at the University of Wisconsin at Madison, who worked with IBM on the project.
The chip's ability to adapt to types of information it was not specifically programmed to expect is a key feature.
Tononi said: "There is a lot of work to do, but the most important thing is usually the first step, and this is not one step, it is a few steps."
Technologists have long imagined computers that learn like humans. Google's and iPhone servers can be programmed to predict certain behavior based on past events. But the techniques being explored by IBM and other companies and university research labs around "cognitive computing" could lead to chips better able to adapt to unexpected information.
IBM's interest in the chips lies in their potential to help process real-world signals such as temperature, sound and motion and make sense of them for computers.
IBM, based in Armonk, New York, is a leader in the movement to link physical infrastructure, such as power plants or traffic lights, to information technology, such as servers and software that help regulate their functions. Such projects can be made more efficient with tools to monitor the myriad analog signals present in those environments.
Dharmendra Modha, project leader for IBM Research, said the new chips have parts that behave like digital "neurons" and "synapses" that make them different than other chips. Each "core," or processing engine, has computing, communication and memory functions.
"You have to throw out virtually everything we know about how these chips are designed," he said. "The key difference really is the memory and the processor are very closely brought together. There is a massive, massive amount of parallelism."
The project is part of the same research that led to IBM's announcement in 2009 that it had simulated a cat's cerebral cortex, the thinking part of the brain, using a huge supercomputer. Using progressively bigger supercomputers, IBM had previously simulated 40 percent of a mouse's brain in 2006, a rat's full brain in 2007, and 1 percent of a human's cerebral cortex in 2009.
A computer with the power of the human brain is not yet near. But Modha said the latest development is an important step.
"It really changes the perspective from 'What if?' to 'What now?'" Modha said. "Today we proved it was possible. There have been many skeptics, and there will be more, but this completes in a certain sense our first round of innovation."
- About Us
- |
- Terms of Use
- |
-
RSS
- |
- Privacy Policy
- |
- Contact Us
- |
- Shanghai Call Center: 962288
- |
- Tip-off hotline: 52920043
- 沪ICP证:沪ICP备05050403号-1
- |
- 互联网新闻信息服务许可证:31120180004
- |
- 网络视听许可证:0909346
- |
- 广播电视节目制作许可证:沪字第354号
- |
- 增值电信业务经营许可证:沪B2-20120012
Copyright © 1999- Shanghai Daily. All rights reserved.Preferably viewed with Internet Explorer 8 or newer browsers.