Feng Feng

Feng Feng received the B.Eng. degree in Tianjin University, Tianjin, China, in 2012, and the Ph.D. degree in the School of Microelectronics at Tianjin University, Tianjin, China, and the Department of Electronics at Carleton University, Ottawa, ON, Canada, in 2017. From 2017 to 2020, he was a Postdoctoral Fellow in the Department of Electronics at Carleton University, Ottawa, ON, Canada. In 2020, he joined the School of Microelectronics at Tianjin University, Tianjin, China, where he is currently a Full Professor. Dr. Feng has authored and co-authored over 200 IEEE journal and conference papers including over 50 IEEE TMTT papers. His research interests include electromagnetic parametric modeling and design optimization algorithms, deep neural network modeling method, space mapping algorithm and surrogate model optimization, electromagnetic centric multiphysics modeling and optimization, and quantum computing in computational electromagnetics. Dr. Feng is the Chair of the IEEE MTT-S Technical Committee on Design Automation (TC-2) and a member of the IEEE MTT-S Working Group on AI and Machine Learning Based Technologies for Microwaves in the MTT-S Future Directions Committee. He is the TPC Chair of the 2025 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO 2025). He was the General Chair of the 2021 IEEE MTT-S Young Professionals Workshop on Electromagnetic Modeling and Optimization (EMO 2021) and the General Co-Chair of the IEEE MTT-S Young Professionals Workshop on EMO from 2022 to 2024. He serves as an Associate Editor for IEEE MICROWAVE AND WIRELESS TECHNOLOGY LETTERS, a Guest Editor for IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES of Special Issues of NEMO 2025, and a Guest Editor for IEEE MICROWAVE MAGAZINE of Special Issues of Young Professionals Workshop on EMO. He has been selected as an IEEE MTT-S Outstanding Young Professional Lecturer since 2025.

Artificial neural network (ANN) techniques are important techniques for microwave computer-aided design (CAD) to perform forward/inverse modeling for active/passive components to enhance circuit design. With measured or simulated data of microwave devices, ANNs can be trained to learn relevant microwave relationships which are otherwise computationally expensive or for which efficient analytical formulas are not available. By training an ANN using data from electromagnetic (EM)/physics simulations, one can use the trained ANN as models for microwave devices to replace the EM/physics models, which are typically CPU-intensive, to significantly accelerate circuit design with EM/physics-level accuracies. ANNs can help address two of the frequently encountered challenges in microwave CAD: One is the computationally expensive challenge in forward modeling, and the other is the no-analytical-equation challenge in the inverse design. To improve the accuracy and reliability of ANN modeling and design optimization, the knowledge-based neural network (KBNN) has been developed. The knowledge-based approach combines neural networks with prior knowledge to build models. The neuro-TF modeling approach, which integrates neural networks with transfer functions, has emerged as an attractive candidate in EM parametric modeling in recent years. The ANN has also been trained to learn the complex and high-dimensional relationships between inputs and outputs in the inverse problems. The trained ANN models provide fast answers of EM/multi-physics behaviors of microwave components when geometrical parameters are repetitively changed and can be used in high-level design.