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 part introduces the role of artificial intelligence in the analysis, modelling, design and optimisation of electromagnetic devices and systems for telecommunications.
2. Fundamentals of machine learning and statistical models
The second unit covers the main machine-learning algorithms, with attention to their interpretation, training data, feature selection, validation and performance assessment criteria.
3. Neural networks and deep learning for electromagnetic applications
The third part deals with the use of neural networks and deep-learning models for the prediction of electromagnetic parameters and the modelling of complex devices and systems.
4. AI for the design and optimisation of electromagnetic devices
The fourth unit focuses on the use of artificial intelligence techniques for assisted design and optimisation of antennas, metamaterials, RF circuits and telecommunication components.
5. Integration of AI into simulation workflows
The fifth part addresses the integration of AI models with numerical methods and electromagnetic simulation tools, with attention to computational cost reduction and generalisation capability.
6. Reliability, limitations and critical use of predictive models
The final part is devoted to the critical assessment of trained models, considering data quality and quantity, computational complexity, robustness, reliability of results and the epistemological limits of artificial intelligence in scientific and engineering contexts.
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
1. Introduction to artificial intelligence for electromagnetic engineeringThe first part introduces the role of artificial intelligence in the analysis, modelling, design and optimisation of electromagnetic devices and systems for telecommunications.
2. Fundamentals of machine learning and statistical models
The second unit covers the main machine-learning algorithms, with attention to their interpretation, training data, feature selection, validation and performance assessment criteria.
3. Neural networks and deep learning for electromagnetic applications
The third part deals with the use of neural networks and deep-learning models for the prediction of electromagnetic parameters and the modelling of complex devices and systems.
4. AI for the design and optimisation of electromagnetic devices
The fourth unit focuses on the use of artificial intelligence techniques for assisted design and optimisation of antennas, metamaterials, RF circuits and telecommunication components.
5. Integration of AI into simulation workflows
The fifth part addresses the integration of AI models with numerical methods and electromagnetic simulation tools, with attention to computational cost reduction and generalisation capability.
6. Reliability, limitations and critical use of predictive models
The final part is devoted to the critical assessment of trained models, considering data quality and quantity, computational complexity, robustness, reliability of results and the epistemological limits of artificial intelligence in scientific and engineering contexts.
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.