Wednesday, November 18, 2009

IBM Computer is Like a Human Brain...Sort of

IBM Computer is Like a Human Brain. Sort of

At the Supercomputing Show in Portland, Oregon, IBM researchers announced that they are much closer to making a computer that can simulate the human brain. According to the researchers, they've reached a couple of major milestones in the project. One is performing the first real-time cortical simulation of the brain that goes beyond that of a cortex. The other is the development of an algorithm that maps the connections between cortical and subcortical areas in the brain, using IBM's Blue Gene super computing architecture.

The IBM researchers, working in collaboration with scientists from Stanford, the University of Wisconsin, Cornell, Columbia University Medical Center, and the University of California at Merced, would like to ultimately make a computer that can evaluate and act on data just like a human brain. The computer would also use similar amounts of space and energy as our brains do.

"Learning from the brain is an attractive way to overcome power and density challenges faced in computing today. As the digital and physical worlds continue to merge and computing becomes more embedded in the fabric of our daily lives, it's imperative that we create a more intelligent computing system that can help us make sense of the vast amount of information that's increasingly available to us, much the way our brains can quickly interpret and act on complex tasks," said Josephine Cheng, a Fellow and lab director of IBM Research-Almaden.

The research is part of a Defense Advanced Research Projects Agency (DARPA) initiative called Systems of Neuromorphic Adaptive Plastic Scalable Eletronics (SYNAPSE). DARPA recently awarded the researchers $16.1 million for Phase 1 of the project. The cortical simulator was run on the Dawn Blue Gene/P supercomputer at Lawrence Livermore National Laboratory. The supercomputer has 144TB of memory and 147,456 processors. The algorithm, which is called BlueMatter, allows scientists to experiment with mathematical hypotheses about how brain structure affects function when combined with the cortical simulator.

The researched say that as the amount of critical data and information continues to rapidly grow, businesses will have to find ways to adapt and make quick decisions. This "brain-like" computer will pull together information to help businesses come up with accurate, fast, and logical responses to data they receive.

No comments: