Date：2025/2/6 11:00-12:00
Location：R101, CSIE
Speakers：Dr. Qinru Qiu
Host：張原豪教授
Abstract:
IoT and edge devices require energy-efficient and adaptive sensing and computation to operate reliably in dynamic environments. Inspired by biological neural systems, spiking neural networks (SNNs) and neuromorphic computing provide an event-driven, temporally rich, and energy-efficient framework for processing multivariate time-series from sensor readings. This talk presents our recent work on SNN-based temporal pattern detection, classification, and sequence generation using spike-based representations, where information is encoded in spike timing and inter-spike intervals to enable significant energy savings. To support online adaptation, we introduce Spatiotemporal Online Learning for Synaptic Adaptation (SOLSA), an efficient learning algorithm that jointly adapts synaptic weights and temporal filters with substantially lower memory and computational cost than backpropagation-through-time while achieving higher accuracy. We also discuss low-complexity spike-encoder architectures for converting multichannel sensor data into sparse spike trains, and show how in-hardware online learning relaxes encoder precision requirements, enabling robust and cost-effective near-sensor intelligence for edge applications.
Biography:
Dr. Qinru Qiu received her PhD in Electrical Engineering from University of Southern California in 2001. She is currently a Distinguished Professor in the Department of Electrical Engineering and Computer Science at Syracuse University. Dr. Qiu is a fellow of IEEE and a distinguished member of ACM. She also is a recipient of NSF CAREER award in 2009 and IEEE Region 1 Technological Innovation award in 2020. She serves as an associate editor of multiple journals including IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Computers, IEEE Transactions on Cognitive and Developmental Systems, etc. She has also served as a technical program committee member of many conferences including DAC, ICCAD, ISLPED, DATE, etc. She is the director of the NSF I/UCRC (Industry University Collaborative Research Center) ASIC (Alternative Sustainable and Intelligent Computing) Center Syracuse Site.