Seminar & Colloquium
[세미나: 3월 7일(화), 오전 10시] Prof. Jianshi Tang, Tsinghua University
Title
Memristor-based Energy-Efficient Neuromorphic Computing
Speaker
Prof. Jianshi Tang, Tsinghua University
Biography
Prof. Jianshi Tang is currently an Associate Professor in the School of Integrated Circuits at Tsinghua University, where he graduated with a BS degree in 2008. He received his PhD degree in Electrical Engineering from University of California, Los Angeles in 2014. From 2015 to 2019, he worked at IBM Watson Research Center. He has received several awards including the MIT Technology Review “35 Innovators Under 35” China, NT18 “Best Young Scientist Award”, IEEE Brain Best Paper Award, etc. His current research mainly focuses on emerging memory and neuromorphic computing. Prof. Tang has published more than 140 journal articles and conference proceedings, including Nature Nanotechnology, Nature Electronics, Nature Communications, Science Advances, Advanced Materials, IEDM, etc. His work has been cited over 9000 times, and also included in the list of “Best Papers in Beijing Area 2020”. He has also filed more than 140 patents, 50 of which are granted. Prof. Tang is on the Editorial Board of several journals including Journal of Semiconductors and Frontiers. He is an IEEE senior member, and served as Technical Program Committee Member for IEDM, IEEE-NANO, EDTM, CSTIC, etc.
| Date | Tuesday, March 7th, 2023
| Time | 10:00 ~
| Venue | 33동 125호(WCU 다목적실)
[Abstract]
In the past decade, the rapid growth of artificial intelligence demands for intelligent computing chips. However, the continuous increase of computing power and energy efficiency for conventional chips with von Neumann architecture face critical challenges amid the slowdown of Moore’s law scaling. Inspired by human brain, computing-in-memory with emerging devices, such as memristors, has emerged as a promising neuromorphic paradigm to break the von Neumann bottleneck. Tremendous progress has been recently made in the developments of oxide-based memristors as neuromorphic devices, such as artificial synapses, neurons as well as dendrites. In this talk, I will first talk about the hardware challenges for artificial intelligence and the motivation for neuromorphic computing. Then I will discuss the key questions and bottlenecks for memristor-based neuromorphic computing. Recent research progress to address those questions will be presented, from device optimization and process integration to architecture design and chip demonstrations. Brain-inspired dendritic computing and energy-efficient reservoir computing with dynamic memristors will also be presented. At the end, I will highlight future research directions and challenges for memristor-based neuromorphic computing.
| Host | 김상범 교수(02-880-7359)