Speaker: Prof. Kwabena Boahen
Affiliation: Stanford University
Abstract: Deep Neural Networks (DNNs) replace the brain’s spike-trains with instantaneous rates that are updated once every time-step. They have proven to be extremely powerful, successfully tackling tasks that were thought to be impossible just a decade ago. The current quest is to deploy DNNs on devices that communicate by radio and are powered by batteries or harvested energy (e.g., mobile phones or IoT end-points, respectively). These entirely wireless devices—projected to reach 20 billion by 2020—require much more energy-efficient computing platforms. A promising brain-inspired approach, known as neuromorphic computing, maps DNN’s discrete-time rates (functional level) to continuous-time spikes (hardware level), but its potential is yet to be realized. In spiking neuromorphic hardware, instead of communicating and computing every time-step (clock-driven operation), communicating and computing only happens when a spike occurs (event-driven operation). Thus, communicational and computational load is reduced if each rate-update requires less than one spike (on average). And also if mapping rates to spikes does not degrade performance. Otherwise the network’s size must be increased to compensate. I will argue that spike-based neuromorphic computing’s potential energy-savings can be maximized by exploiting analog computation and communication and I will present my group’s progress in designing these mixed-signal neuromorphic chips and in reducing the overhead incurred mapping DNNs onto them.
Biography: Kwabena Boahen is a Professor of Bioengineering and Electrical Engineering at Stanford University, where he directs the Brains in Silicon Lab. He is a neuromorphic engineer who is using silicon integrated circuits to emulate the way neurons compute, and linking the seemingly disparate fields of electrical engineering and computer science with neurobiology and medicine. His interest in neural nets developed soon after he left his native Ghana to pursue undergraduate studies in Electrical and Computer Engineering at Johns Hopkins University, Baltimore, in 1985. He went on to earn a doctorate in Computation and Neural Systems at the California Institute of Technology in 1997. From 1997 to 2005 he was on the faculty of University of Pennsylvania, Philadelphia PA, where he held the inaugural Skirkanich Term Junior Chair. His scholarship is widely recognized, with over ninety publications to his name, including a cover story in the May 2005 issue of Scientific American that featured his lab’s work on a silicon retina that could be used to give the blind sight. He has received several distinguished honors, including the National Institutes of Health Director’s Pioneer Award (2006). He was elected a fellow of the American Institute for Medical and Biological Engineering (2016) and of the Institute of Electrical and Electronic Engineers (2016), in recognition of his lab’s work on Neurogrid, a specialized hardware platform that enables the cortex’s inner workings to be simulated in real time—something outside the reach of even the fastest supercomputers. His 2007 TED talk, “A computer that works like the brain”, has been viewed over half-a-million times. He is cofounder of and scientific advisor to Femtosense, a start-up commercializing his Stanford group’s neuromorphic computing techniques.
Date(s) - May 20, 2019
12:30 pm - 1:30 pm
EE-IV Shannon Room #54-134
420 Westwood Plaza - 5th Flr., Los Angeles CA 90095