The course aims to provide students with an advanced understanding of artificial intelligence techniques applied to electromagnetic engineering, particularly for the analysis, modeling, design, and optimization of devices and systems for telecommunications.
By the end of the course, students will be able to:
- critically understand and analyze the main machine learning algorithms, with specific applications to electromagnetic problems;
- implement AI-based models for predicting electromagnetic parameters and assisting in the design of antennas, metamaterials, and RF circuits;
- integrate AI techniques within numerical simulation workflows;
- assess model performance in terms of data quality, computational complexity, and generalization ability;
- use advanced software tools for training, validating, and testing neural networks and statistical models;
- develop a critical and informed approach to the use of artificial intelligence in scientific and engineering contexts, with attention to result reliability and the epistemological limitations of predictive models.
By the end of the course, students will be able to:
- critically understand and analyze the main machine learning algorithms, with specific applications to electromagnetic problems;
- implement AI-based models for predicting electromagnetic parameters and assisting in the design of antennas, metamaterials, and RF circuits;
- integrate AI techniques within numerical simulation workflows;
- assess model performance in terms of data quality, computational complexity, and generalization ability;
- use advanced software tools for training, validating, and testing neural networks and statistical models;
- develop a critical and informed approach to the use of artificial intelligence in scientific and engineering contexts, with attention to result reliability and the epistemological limitations of predictive models.
teacher profile teaching materials
The first module, Foundations, introduces the fundamental concepts of artificial intelligence and electromagnetic theory integration. It provides students with a shared vocabulary and methodological grounding in both fields to facilitate interdisciplinary understanding.
The second module, Supervised Learning for EM Modeling, explores how labeled data from electromagnetic simulations or experiments can be used to train predictive models. Emphasis is placed on regression tasks, neural networks, and data-driven approximation of field distributions and device responses.
In the third module, students examine Physics-Informed Neural Networks (PINNs) and selected unsupervised learning techniques. This module emphasizes the embedding of Maxwell’s equations directly into the learning process to ensure physically consistent predictions, especially in situations with limited training data.
The fourth module, Surrogate Modeling and Model Order Reduction, addresses strategies to replace computationally expensive full-wave simulations with fast, data-driven models. Students learn how to build compact and efficient surrogates that preserve physical fidelity while significantly accelerating design processes.
The fifth module focuses on Design Optimization, highlighting how AI techniques can reconstruct material properties, geometries, or source distributions from measurement or simulated data. It also covers constrained optimization in high-dimensional spaces using AI-enhanced solvers.
The final module, Advanced Applications and Integration with EM Software, demonstrates how to embed AI models into industrial electromagnetic workflows using tools like CST Studio Suite, HFSS, and MATLAB. Students apply their skills to real-world challenges such as antenna synthesis, metamaterial characterization, and intelligent electromagnetic environment modeling.
S. Haykin, Neural Networks and Learning Machines, 3rd ed., Pearson
C. M. Bishop, Pattern Recognition and Machine Learning, Springer
S. M. Rao, Time Domain Electromagnetics, Academic Press
Additional resources:
Goodfellow, Bengio, Courville, Deep Learning, MIT Press
Krizhevsky et al., ImageNet Classification with Deep Convolutional Neural Networks, NIPS
Selected articles from international scientific journals, including:
IEEE Trans. on Antennas and Propagation
IEEE Trans. on Microwave Theory and Techniques
IEEE Trans. on Neural Networks and Learning Systems
Nature Machine Intelligence
EPJ Applied Metamaterials
Other materials:
Lecture notes by the instructor: custom teaching materials will be provided throughout the course, including code notebooks, conceptual diagrams, datasets, and problem sets, designed to support learning and facilitate practical applications.
Mutuazione: 20810542 ARTIFICIAL INTELLIGENCE FOR ELECTROMAGNETIC TECHNOLOGIES in Ingegneria elettronica per l'industria e l'innovazione LM-29 TOSCANO ALESSANDRO
Programme
The course is organized into 6 modules, each with a specific focus.The first module, Foundations, introduces the fundamental concepts of artificial intelligence and electromagnetic theory integration. It provides students with a shared vocabulary and methodological grounding in both fields to facilitate interdisciplinary understanding.
The second module, Supervised Learning for EM Modeling, explores how labeled data from electromagnetic simulations or experiments can be used to train predictive models. Emphasis is placed on regression tasks, neural networks, and data-driven approximation of field distributions and device responses.
In the third module, students examine Physics-Informed Neural Networks (PINNs) and selected unsupervised learning techniques. This module emphasizes the embedding of Maxwell’s equations directly into the learning process to ensure physically consistent predictions, especially in situations with limited training data.
The fourth module, Surrogate Modeling and Model Order Reduction, addresses strategies to replace computationally expensive full-wave simulations with fast, data-driven models. Students learn how to build compact and efficient surrogates that preserve physical fidelity while significantly accelerating design processes.
The fifth module focuses on Design Optimization, highlighting how AI techniques can reconstruct material properties, geometries, or source distributions from measurement or simulated data. It also covers constrained optimization in high-dimensional spaces using AI-enhanced solvers.
The final module, Advanced Applications and Integration with EM Software, demonstrates how to embed AI models into industrial electromagnetic workflows using tools like CST Studio Suite, HFSS, and MATLAB. Students apply their skills to real-world challenges such as antenna synthesis, metamaterial characterization, and intelligent electromagnetic environment modeling.
Core Documentation
Main textbooks:S. Haykin, Neural Networks and Learning Machines, 3rd ed., Pearson
C. M. Bishop, Pattern Recognition and Machine Learning, Springer
S. M. Rao, Time Domain Electromagnetics, Academic Press
Additional resources:
Goodfellow, Bengio, Courville, Deep Learning, MIT Press
Krizhevsky et al., ImageNet Classification with Deep Convolutional Neural Networks, NIPS
Selected articles from international scientific journals, including:
IEEE Trans. on Antennas and Propagation
IEEE Trans. on Microwave Theory and Techniques
IEEE Trans. on Neural Networks and Learning Systems
Nature Machine Intelligence
EPJ Applied Metamaterials
Other materials:
Lecture notes by the instructor: custom teaching materials will be provided throughout the course, including code notebooks, conceptual diagrams, datasets, and problem sets, designed to support learning and facilitate practical applications.
Attendance
Attendance is not mandatory, but it is strongly recommended. Active participation in lectures, practical sessions, and project activities greatly enhances the acquisition of both theoretical and practical skills and offers students the opportunity to engage directly with the instructor for in-depth discussion of course topics.Type of evaluation
The assessment consists of three main components: Written exam: a test including theoretical and applied questions based on the topics covered during lectures. The goal is to assess the student’s understanding of core concepts, ability to apply AI methods to electromagnetic problems, and command of technical language. Individual or group project: development and oral presentation of an original project that applies artificial intelligence techniques to electromagnetic analysis or design (e.g., antennas, metamaterials, RF signals). The project will be evaluated thoroughly based on methodology, results, and presentation. Continuous assessment: includes active participation in class, completion of assigned exercises, and possible intermediate presentations. A written midterm test may also be administered. The final grade will consider technical accuracy, clarity of communication, critical thinking skills, originality of proposed solutions, and completeness of the project.