Title: Building Brain-Like Computers – Small, Cool, and Robust: A Novel Paradigm for Analog Neuron Circuit Design
Abstract: As semiconductor technologies continue to scale further into the nanometer regime, it is important to study how non-traditional computer architectures may be uniquely suited to take advantage of the novel behavior observed for many emerging technologies. Neuromorphic computing, which is inspired by the working mechanism of human brain, represents a type of non-traditional architecture encompassing evolutionary and holds great promise for many important engineering and scientific applications. In this talk, I will present our research work on energy efficient analog neuron integrated circuit (IC) design in neuromorphic computing systems and its exploration to emerging applications. Spike time dependent encoding efficiently maps a signal’s amplitude information into a spike time sequence that offers perfect recovery for band limited stimuli. The nonlinear node based delay feedback reservoir represents a class of dynamic processors that meet the requirements of high dimensionality and finite memory. Three dimensional (3D) integration with neuromorphic IC provides high system speed, high density, low power consumption, and small footprint. Finally, I will show the application of the proposed design and methodology by looking at the problem of problem of high rate data detection and channel estimation.
Speaker Bio: Yang (Cindy) Yi is an Assistant Professor in the Department of Electrical Engineering and Computer Science (EECS) at University of Kansas (KU). Prior to joining the faculty at KU, she has been working on various research topics in the area of integrated circuits and systems at Texas A&M University, Freescale, IBM, Intel, and Texas Instruments (TI). She obtained her Ph.D. in Computer Engineering at Texas A&M University, the M.S. and B.S. in Electrical Engineering at Shanghai Jiao Tong University. Her research interests lie in general areas in Very Large Scale Integrated (VLSI) Circuits and Systems, Neuromorphic Computing, Computer Aided Design (CAD), and Emerging Nano-electronic Device. Yang (Cindy) Yi has been invited to serve as an editorial board member for several international journals including IJCNE, EJAET, and JSAM, a frequent panelist for National Science Foundation (NSF) and Air Force Office of Scientific Research (AFSOR) technical proposal review panels, and a member of Technical Program Committee (TPC) for various international conferences including ICC, EMC, GLOBECOM, ISQED, ASQED, ICNC, ICCVE, ACM Student Research Competition in ICCAD, and etc. She received the United States Air Force (USAF) Summer Faculty Fellowship, Miller Professional Development Award for Distinguished Research in 2016, KU Miller Scholar, NSF EPSCoR First Award, USAF Summer Faculty Fellowship, KU New Faculty General Research Award in 2015, Air Force Research Lab (AFRL) Visiting Faculty Research Fellowship, University Academic Program Faculty Scholar, University Outstanding Service Award, and Texas Instruments (TI) University Program Equipment Award in 2014. Yang (Cindy) Yi’s research has been funded by NSF, Department of Defense (DoD), NSF EPSCoR, AFRL, AFSOR, State of Kansas, and several industrial companies.