The seminar series aims to: Provide the knowledge necessary to develop advanced models of passive and active devices, circuits, and systems. Neural modeling techniques are introduced and contextualized within the high-frequency, RF, and microwave domains. Present advanced optimization techniques, comparing them with classical approaches and highlighting their relevance and applications in neural network modeling. Introduce the fundamental concepts of deep learning and artificial intelligence, with a constant focus on their impact and potential in high-frequency design. Prof. QiJun Zhang is a full Professor at Carleton University in Ottawa. For decades, he has been leading research in the field of advanced modeling and optimization. He is recognized worldwide as an expert in neural network modeling, deep learning techniques, and artificial intelligence. He is currenly chairing several Committees and international groups active in the fields of deep learning, artificial intelligency and neural network based modelling. He is spending his sabbatical leave here a DETwhere he joined the group of Marco Pirola.

Guest Lecture: QI-JUN ZHANG received the PhD degree in Electrical Engineering from McMaster University, Hamilton, Canada in 1987. He was a Research Engineer in Optimization Systems Associates Inc., (Dundas, Ontario, Canada) during 1988-1990, developing advanced microwave optimization software. He joined the Department of Electronics, Carleton University, Ottawa, Canada in 1990, where he is presently a Chancellor’s Professor. During 2025/2026 academic year, he is a Visiting Professor with Dipartimento di Elettronica e Telecomunicazioni, Politecnico di Torino, Torino, Italy. His research interests include AI/machine learning and optimization techniques for RF/microwave design and has more than 360 publications in the area. He is an Author of the book Neural Networks for RF and Microwave Design(Boston: Artech House, 2000),twice a Guest-Editor for the Special Issues on Applications of Artificial Neural Networks (ANN) for RF/Microwave Design for theInternational Journal of RF/Microwave Computer-Aided Engineering(1999, 2002), a Guest Co-Editor for the Special Issue on Machine Learning in Microwave Engineering for the IEEE Microwave Magazine(October 2021), and Guest-Editor for the Special Issue on AI/Machine Learning Technologies for Microwaves in the IEEE Transactions on Microwave Theory and Techniques(November 2022). Dr. Zhang is a Fellow of the IEEE, a Fellow of the Canadian Academy of Engineering, and a Fellow of the Engineering Institute of Canada. He is a Topic Editor for theIEEE Journal of Microwaves. He co-founded and co-chairs the Working Group on AI and Machine Learning Based Technologies for Microwaves in the Future Directions Committee of the IEEE MTT Society. Content of the Seminar Series: 1. Introduction 2. Machine Learning Methods and Structures and Their Applications o Multilayer Perceptron and Application Examples o Feedforward Neural Networks o Knowledge-based Neural Networks, and Application Examples o Recurrent Neural Networks, and Application Examples o Long Short Term Memory (LSTM) and Application Examples o Convolutional Neural Networks and Application Examples o Attention-based Neural Networks and Application Examples o Other Methods and Structures 3. Development of Neural Networks o Neural Network Formulations o Data Generation, Issues and Guidelines o Neural Network Training, Overlearning, Issues and Guidelines o Introduction to Neural Network Training Algorithms o Backpropagation o Gradient-based training algorithms o Training with regularization o Stochastic Gradient Descent o Adam (Adaptive moment estimation) 4. Application of Machine Learning for Microwave Passive and Active Modeling o Electromagnetic parameterized model o Electromagnetic based Neuro-Transfer Function (TF) Model o Neural-TF Modeling by Learning from Electromagnetic Sensitivity Data o Multiphysics based Modeling o ANN Methods for Microwave Device Modeling o Neuro-Space Mapping (Neuro-SM) for Microwave Device Modeling o Machine Learning Methods for Behavioral Modeling of Nonlinear Microwave Circuits 5. Further Aspects and Trend of AI and Machine Learning for Microwave Engineering Brief perspectives of further developments of machine learning in microwave design automation; Device, circuits and system level applications; AI/ML in system operations for wireless networks, electromagnetic imaging, radar sensing and signal processing for autonomous systems. Reference Material: Q.J. Zhang and K.C. Gupta, Neural Networks for RF and Microwave Design, Boston, MA: Artech House, 2000. Q.J. Zhang, K.C. Gupta and V.K. Devabhaktuni, “Artificial neural networks for RF and microwave design: from theory to practice,” IEEE Trans. Microwave Theory and Techniques, vol. 51, no. 4, pp. 1339-1350, April 2003. F. Feng, W.C. Na, J. Jin, J.N. Zhang, W. Zhang, and Q.J. Zhang, "Artificial neural networks for microwave computer-aided design: the state of the art," IEEE Transactions on Microwave Theory and Techniques, vol. 70, no. 11, pp. 4597-4619, Nov. 2022. S.D. Campbell and D.H. Werner, Advances in Electromagnetics Empowered by Artificial Intelligence and Deep Learning, IEEE Express/Wiley, Piscataway, New Jersey, 2023. Q.J. Zhang, Guest Editor, Special Issue on AI/ML based Technologies for Microwaves, IEEE Transactions on Microwave Theory and Techniques, vol. 70, no. 11, Nov. 2022.

In presenza

Sviluppo di project work in team

P.D.2-2 - Maggio