Cognitive computing project aims to reverse-engineer the mind
source: http://blog.wired.com/gadgets/2009/02/cognitive-compu.html
-
-
- lvp
- added this
Imagine a computer that can process text, video and audio in an instant, solve problems on the fly, and do it all while consuming just 10 watts of power.
It would be the ultimate computing machine if it were built with silicon instead of human nerve cells.
Compare that to current computers, which require extensive, custom programming for each application, consume hundreds of watts in power, and are still not fast enough. So it's no surprise that some computer scientists want to go back to the drawing board and try building computers that more closely emulate nature.
"The plan is to engineer the mind by reverse-engineering the brain," says Dharmendra Modha, manager of the cognitive computing project at IBM Almaden Research Center.
It would be the ultimate computing machine if it were built with silicon instead of human nerve cells.
Compare that to current computers, which require extensive, custom programming for each application, consume hundreds of watts in power, and are still not fast enough. So it's no surprise that some computer scientists want to go back to the drawing board and try building computers that more closely emulate nature.
"The plan is to engineer the mind by reverse-engineering the brain," says Dharmendra Modha, manager of the cognitive computing project at IBM Almaden Research Center.
-
- groups:
- Tech, Green, Earth and Science
-
- tags:
- Green, Tech, Earth and Science, Brain, 8 more
-
-
cybexg
-
Still suffers from the local minimum problem. Not quite 20 years ago, there was this really bright kid developing a new math that utilized n-dim linear pockets bounded by an error with which to estimate the corresponding n-dim non-linear space. The idea was that the estimated linear pocket would provide information with which you could predict and avoid local minimums with. That way, the error propagation learning techniques could be adjusted avoid getting stuck in those minimums.
Note, I'm not even commenting about the encoding problem.
I'm curious how they are approaching some of the "hard" problems.
- 3 years ago
-
cybexg
