| Feb 06, 2012 |
DARPA's SyNAPSE program name one of best innovations of 2011
|
|
(Nanowerk News) Computers are constrained by physical limits, as well as the requirement for humans to program how computers interact with their environments. In contrast the human brain autonomously processes information and learns from its environment. If available, neuromorphic electronic machines, computers that function more like a brain, may enable autonomous computational solutions for real-world problems with many complex variables.
|
|
The DARPA Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) program seeks to realize this goal by creating electronic systems inspired by the human brain that can understand, adapt and respond to information in fundamentally different ways than traditional computers.
|
|
Featured recently in Scientific American as one of 10 World Changing Ideas, and in The Washington Post as one of the Best innovation moments in 2011, IBM researchers working on DARPA's SyNAPSE program were cited for unveiling a "new generation of experimental computer chips designed to emulate the brain's abilities for perception, action and cognition."
|
|
"If we're successful," said Jay Schnitzer, director, Defense Sciences Office, "we'll have access to flexible hardware capable of learning without reprogramming for various control, information processing and decision-making applications. An on-board, neuromorphic computer chip could tremendously improve the capabilities of unmanned ground and aerial vehicle platforms."
|
|
While current computers are organized into distinct processor and memory units that function in accordance with their programming, the brain is organized as an intimate and distributed web of many, many simpler processors (neurons) and connections (synapses) that spontaneously communicate and learn their functions. Using knowledge of the brain's organization as a platform, SyNAPSE is developing integrated circuits with high densities of electronic devices and integrated communication networks that approximate the function and connectivity of neurons and synapses. Continuing efforts seek to improve the production of electronic components, create enhanced system architecture and design tools, and realize virtual environments for training and testing.
|
