Design Exploration and Optimization News
Design Exploration and Optimization Resources
December 4, 2001
Technology has certainly gotten faster and smarter, but the human brain remains the clear champ when it comes to raw performance. We’ve written before about attempts to simulate brain function electronically; now researchers at Boise State University have launched a project to build a new computing architecture that mimics the brain called “CIF: Small: Realizing Chip-scale Bio-inspired Spiking Neural Networks with Monolithically Integrated Nano-scale Memristors.”
Armed with a three-year, $500,000 National Science Foundation grant, the group is targeting memristors as the basis of its new chips, and will rely on new mathetmatical algorithms that explain the electrical interaction between synapses and neurons.
A memristor is a resistor that, according to the Boise State website, “can be programmed to a new resistance by application of electrical pulses and remembers its new resistance value once the power is removed.” Boise State is one of the few facilities in the world that can build memristors.
“By employing these models in combination with a new device technology that exhibits similar electrical response to the neural synapses, we will design entirely new computing chips that mimic how the brain processes information,” said Barney Smith, principal investigator on the grant.
The first of the new neuron chips the team plans to build could be fabricated within the next few weeks.
In a not-really-related, but amazing nonetheless development, one University of Washington researcher recently used his thoughts to control another researcher’s movements. You can read about the brain-to-brain communication experiment