YP Ambassador
Hanzhi Ma
Young Professional Ambassador
Hanzhi Ma
Term 2025-2026
Assistant Professor
Zhejiang University
Zhejiang, China
Hanzhi Ma is an Assistant Professor at Zhejiang University and an Adjunct Assistant Professor at University of Illinois at Urbana-Champaign (UIUC). She received her B.S. degree and Ph.D. degree in Electrical Engineering from Zhejiang University, Hangzhou, China, in 2017 and 2022, respectively under the supervision of Prof. Er-Ping Li. She has carried out research at Electromagnetics Laboratory in UIUC in Fall 2018, Summer 2019, Fall 2021, and Spring 2022 based on ZJU-UIUC joint Ph.D. program under the guidance from Prof. Andreas C. Cangellaris and Prof. Jose Schutt-Aine, and visited Electromagnetic Compatibility Laboratory at Missouri University of Science and Technology as a visiting scholar in Summer 2016 under the guidance from Prof. James Drewniak. Dr. Ma has been working on electromagnetic compatibility since 2016, with a special focus on signal integrity analysis for neuromorphic chip and machine learning techniques for electromagnetic compatibility, signal and power integrity. She has conducted research on modeling, analyzing, and optimizing of signal integrity for circuits and devices with non-Von Neumann architectures, which are specifically tailored for neuromorphic chips, aiming to provide reliable electronic design automation tools to propel their advancement. Meanwhile, she has been developing machine learning-based modeling and optimization methods to build explainable and principled intelligent tools and systems that can help guide PCB-Package-Chip signal integrity and electromagnetic compatibility design in an adaptive, robust, and efficient way. Dr. Ma has authored or coauthored more than 60 papers. She also serves as the Guest Editor of IEEE Transactions on Components, Packaging and Manufacturing Technology with the special section of “Advances in Heterogeneous Integration for Neuromorphic Computing.”
Talk: Signal Integrity Modeling and Optimization for Neuromorphic Chips
Abstract: Artificial intelligence (AI) is now in the third wave of development and achieving new breakthroughs in many fields such as finance, medical care, education, transportation, and security. Neuromorphic chips, which emulate human brain behavior for efficient execution of AI operations, while overcoming the “memory wall” issue inherent in Traditional computing architecture, have garnered widespread attention. Neuromorphic chips adopt von Neumann architecture and novel memristive devices, making their signal integrity problems more challenging. As neuromorphic chips evolve towards miniaturization, high integration, and high-speed operation, signal integrity issues will become a significant factor limiting their design and production. Therefore, conducting research on the signal integrity modeling and analysis of neuromorphic chips has significant scientific value and broad industrial application prospects. This presentation provides an overview of neuromorphic chip concepts and circuit architectures, emphasizing the critical role of signal integrity research in their design. The speaker will then proceed to introduce her work and advancements in signal integrity modeling and optimization theories and methods for neuromorphic chips. Additionally, she will showcase the impact of parasitic effects on signal transmission in practical neuromorphic chips, along with the proposed improvement methods. Finally, this presentation will discuss key future research directions in the field of signal integrity for neuromorphic chips.
Zhejiang University
Zhejiang, China
Hanzhi Ma is an Assistant Professor at Zhejiang University and an Adjunct Assistant Professor at University of Illinois at Urbana-Champaign (UIUC). She received her B.S. degree and Ph.D. degree in Electrical Engineering from Zhejiang University, Hangzhou, China, in 2017 and 2022, respectively under the supervision of Prof. Er-Ping Li. She has carried out research at Electromagnetics Laboratory in UIUC in Fall 2018, Summer 2019, Fall 2021, and Spring 2022 based on ZJU-UIUC joint Ph.D. program under the guidance from Prof. Andreas C. Cangellaris and Prof. Jose Schutt-Aine, and visited Electromagnetic Compatibility Laboratory at Missouri University of Science and Technology as a visiting scholar in Summer 2016 under the guidance from Prof. James Drewniak. Dr. Ma has been working on electromagnetic compatibility since 2016, with a special focus on signal integrity analysis for neuromorphic chip and machine learning techniques for electromagnetic compatibility, signal and power integrity. She has conducted research on modeling, analyzing, and optimizing of signal integrity for circuits and devices with non-Von Neumann architectures, which are specifically tailored for neuromorphic chips, aiming to provide reliable electronic design automation tools to propel their advancement. Meanwhile, she has been developing machine learning-based modeling and optimization methods to build explainable and principled intelligent tools and systems that can help guide PCB-Package-Chip signal integrity and electromagnetic compatibility design in an adaptive, robust, and efficient way. Dr. Ma has authored or coauthored more than 60 papers. She also serves as the Guest Editor of IEEE Transactions on Components, Packaging and Manufacturing Technology with the special section of “Advances in Heterogeneous Integration for Neuromorphic Computing.”
Talk: Signal Integrity Modeling and Optimization for Neuromorphic Chips
Abstract: Artificial intelligence (AI) is now in the third wave of development and achieving new breakthroughs in many fields such as finance, medical care, education, transportation, and security. Neuromorphic chips, which emulate human brain behavior for efficient execution of AI operations, while overcoming the “memory wall” issue inherent in Traditional computing architecture, have garnered widespread attention. Neuromorphic chips adopt von Neumann architecture and novel memristive devices, making their signal integrity problems more challenging. As neuromorphic chips evolve towards miniaturization, high integration, and high-speed operation, signal integrity issues will become a significant factor limiting their design and production. Therefore, conducting research on the signal integrity modeling and analysis of neuromorphic chips has significant scientific value and broad industrial application prospects. This presentation provides an overview of neuromorphic chip concepts and circuit architectures, emphasizing the critical role of signal integrity research in their design. The speaker will then proceed to introduce her work and advancements in signal integrity modeling and optimization theories and methods for neuromorphic chips. Additionally, she will showcase the impact of parasitic effects on signal transmission in practical neuromorphic chips, along with the proposed improvement methods. Finally, this presentation will discuss key future research directions in the field of signal integrity for neuromorphic chips.