题目：Digital Integrated Circuits Design 时间：上午10:00 地点：行政楼108会议室 报告人：黄科杰博士

 Abstract: Energy consumption in general computing environment, such as home electronics, data centre, internet of things, artificial intelligence, etc., has been one of the most critical issues. The key underlying problem is that the memory and the processing unit are separated in the conventional Von Neumann system. New computing systems are under focused development to meet the rapidly growing demands of low power, high computing power and intelligent systems. Technological advancements are the major propellant for architectural innovations. The recent resistive non-volatile memory technologies open a new paradigm of the computing system and may revolutionize the computer architecture in near future.

In this talk I will present some recent work on the new computing architecture development by using resistive non-volatile memories with particular emphasis on a recent work where we propose the use of memristor/binary resistive memory as the synapse in the neuromorphic computing. The state-of-art design either utilized SRAM as the synapse to implement a full digital neuromorphic system or employed the opamp and arbitrary waveform generator in their analog neuromorphic system. We are focusing on a novel architecture with the analog neurosynaptic core and digital interface to achieve a high density, low power, flexible and robust neuromorphic system. I will also present the applications and some recent projects based on the proposed neuromorphic chip.

Speaker Bio: Kejie Huang received the B.Sc degree and M.Eng degree from the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China, in 2003 and 2006, respectively, and the Ph.D degree from the Department of Electrical Engineering, National University of Singapore, Singapore, in 2014. Now he is a Research Fellow with the Department of Engineering Product Design, Singapore University of Technology and Design. He has authored or co-authored around 20 papers in international peer-reviewed journals and conference proceedings. He holds four granted international patents, and another three patent applications. His current research interests include low power circuits and systems design using emerging nonvolatile memories, architecture and circuit optimization for reconfigurable computing systems, emerging embedded memory design, and neuromorphic computing system design.