Since the early days in the 1940s, computers have routinely been described as “brains” — giant brains or mathematical brains or electronic brains. Scientists and engineers often cringed at the distorting simplification, but the popular label stuck.
Wait long enough, it seems, and science catches up with the metaphor. The field of “cognitive computing” is making enough progress that the brain analogy is becoming more apt. I.B.M. researchers are announcing on Thursday two working prototype cognitive computer chips.
The chip designs are the result of a three-year project involving I.B.M. and university researchers, supported by the Defense Advanced Research Projects Agency. The academic collaborators are at Columbia University, Cornell University, the University of California, Merced and the University of Wisconsin.
The results to date have been sufficiently encouraging that Darpa is announcing on Thursday that it will commit an additional $21 million to the project, the third round of government funding, which brings the total to $41 million.
The cognitive chips are massively parallel microprocessors that consume very little power. But they also have a fundamentally different design. The two prototype semiconductor cores each has 256 neuronlike nodes. One core is linked to 262,144 synapselike memory modules, while the other is linked to 65,536 such memory synapses.
The researchers call the design a “neurosynaptic core.”
“This is a critical shift away from today’s Von Neumann computing,” said Dharmendra Modha, an I.B.M. researcher who is the project leader. He is referring to the design and step-by-step sequential methods used in current computers, named after the mathematician John Von Neumann.
The new design, Mr. Modha said, should lead to chips suited for tasks that are difficult for computers like pattern recognition. They can learn on their own. “We aren’t there yet, but before long these chips will be able to rewire themselves on the fly,” he said.
Such cognitive chips, Mr. Modha added, will be adept at absorbing and interpreting huge amounts of data from increasingly low-cost digital sensors. For example, cognitive computers — using sensor measurements of air and water temperature, ocean tides, wind patterns and atmospheric pressure — could make more timely and accurate predictions of tsunamis and hurricanes, he said.
Working cognitive-computer chips, analysts say, are an impressive step. “These are building blocks for a new kind of computing,” said Richard Doherty, an analyst at Envisioneering, a technology research firm.
Still, cognitive computing is still years away from the marketplace, and it will more likely complement than replace conventional computers. Even its champions who freely use the brain analogy do so with a sense of humility.
“We’re not trying to build a brain,” Mr. Modha said. “We’re trying draw inspiration from the brain.”
Source: The New York Times