Monday, November 11, 2019 at 4:15pm
Packard Laboratory, 466
19 Memorial Dr W, Bethlehem, PA 18015
Dr. Peng Li, from the University of California at Santa Barbara, will present on "Learning Mechanisms and Hardware Design for Computation with Spiking Neurons"
Abstract: As one form of brain-inspired computing, spiking neural networks (SNN) have recently gained
momentum. This is fueled by in part by advancements in emerging devices and neuromorphic hardware, e.g., availability of Intel Loihi and IBM TrueNorth neuromorphic chips, promising ultra-low energy event-driven processing of large amounts of data. Nevertheless, major challenges are yet to be conquered to make spikebased computation a competitive choice for real-world applications. This talk will present a multi-faceted SNN research approach: 1) empowering SNNs by exploring computationally-powerful feedforward and recurrent architectures; 2) tackling major challenges in training complex SNNs by developing biologically plausible learning mechanisms and error backpropagation operating on top of spiking discontinuities; and 3) enabling efficient FPGA
spiking neural processors with integrated on-chip learning via algorithm-hardware co-optimization.