Researchers at IBM have developed chips that will work almost similar to biological brain’s abilities. They have developed the chip on the basis of non-traditional approaches that will use very less power and space as compared to recent computers that are in market.
These chips are neurosynaptic computing chips that will use latest algorithms and silicon technology and work just like original neurons and synapses.
First two prototypes are already developed by IBM researchers, which are under trials.
Computers using these chips are called as Cognitive Computers. These Cognitive computers are expected to learn through experiences, work on mutual relationships of different tasks or processes, make hypothesis and remember (what has already been happened) and find out results on this. These computers use digital silicon circuits to form “neurosynaptic core” with integrated memory much like synapses, computation processes much like neurons and communication tasks much like axons in the body.
Numerous technological departments, such as neuroscience, nanoscience and supercomputing, worked together through years to develop such cognition in computing devices. The Defense Advanced Research Projects Agency (DARPA) has awarded funds of US $21 million for phase 2 of the Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) project, which will combine researchers and collaborators from IBM, Columbia University, University of California, Cornell University, University of Wisconsin-Madison and Merced.
Comparatively, the human brain—the world’s most sophisticated computer—can perform complex tasks rapidly and accurately using the same amount of energy as a 20 watt light bulb in a space equivalent to a 2 liter soda bottle.
Manager of Cognitive Computing at IBM Almaden Research Center is Darmendra S. Modha.
References and Further Reading:
http://www.ibm.com/smarterplanet/us/en/business_analytics/article/cognitive_computing.html accessed August 18, 2011.