ENERGY | WIRELESS | NANOTECH | MEMS | OPTICS | QUANTUM | 3D | CHIPS | ALGORITHMS

Tuesday, August 20, 2013

#CHIPS: "DARPA Aims for Neural Image Processor"

Processing images 1000-times faster than today is the aspiration of the University of Michigan's neural network chip set funded by the Defense Advanced Research Project Agency (DARPA). By using memristors as artificial synapses in a brain-like architecture the image processor will uses 10,000 less power than today: R. Colin Johnson @NextGenLog


Neural network image processor connects artificial neurons using a crossbar (lower left) of memristors with migrating oxygen vacancies (upper right)that adaptively change its synaptic connection strengths.
Further Reading