>> _css/_system/system.css" rel="stylesheet"/>
确定 取消 应用
学术报告
学术报告

您的位置 : 首页  学术报告

关于美国密苏里科技大学姜立军教授学术报告的通知

2024年5月31日(星期五)11:00-12:00

发布日期 :2024-05-30    阅读次数 :10

题目:Computational Electromagnetics and Machine Learning for Electromagnetic Compatibility , Signal Integrity and Power Integrity 

时间: 2024年5月31日(星期五)11:00-12:00

地点:玉泉校区,行政楼第二会议室

线上会议:腾讯会议ID 317-269-360

报告人:Prof. Lijun Jiang, IEEE Fellow, 

               EMC Lab, Missouri University of S&T

Biograghy: Lijun Jiang received his Bachelor Degree in electrical engineering from the Beijing University of Aeronautics and Astronautics in 1993, Master Degree from the Tsinghua University in 1996, and Ph.D from the University of Illinois at Urbana-Champaign (UIUC) in 2004. From 2004 to 2009, he has been a Postdoc, Research Staff Member, and Senior Engineer at IBM T.J. Watson Research Center. He was the Associate Professor from Dec. 2009 and then the Honorable Associate Professor at the Department of EEE, the University of Hong Kong (HKU), where he received tenure in Jul. 2014.  From Sept. 2022, he was a full professor at the Dept. of EE, the Chinese University of Hong Kong and the Associate Director of Center for Intelligent Electromagnetic Systems (CiEMS).  Since Sept. 2023, he is the Kummer Endowed Professor at EMC Laboratory, Dept. of ECE, Missouri University of Science and Technology. He has worked with Hewlett-Packard and Teradyne as tech lead and manager for high frequency measurement technologies and package designs. His multidisciplinary research activities have resulted in leading research outputs over 180 peer-reviewed journal publications, many international and regional awards, multiple patents, and books/book chapters.  His research interests include heterogeneous electromagnetic modeling methodologies, high speed electronic physical design and EDA solutions, machine learning for SI/PI and EMC/EMI, microwave technologies for material engineering, and optics, etc.

Abstract: In this talk, we will first introduce our CEM progresses in EMC/EMI/SI/PI related modeling and characterization methods. The above-mentioned challenges will be addressed. Together with many other technologies, they serve modern EDA tools as backbones for electronic physical designs.  Facing the blooming machine learning (ML) technologies, we have to find ways to innovate our methods from the algorithm level to the application level.  Hence, in the second part of this talk, we will focus on our recent machine learning and data driven methods for EMC/SI/PI related research.  At the end of this talk, we will show some of our preliminary results in ChatGPT and LLM tools for SI/PI analysis.