-
Name (Acronym)Lab on AI-based Metamaterials & Metastructures Design (LAIM)
-
ECTS2
-
Contact E-mail2025.MAII.LAIM.UniTN.TRENTO.IT@eledia.org
-
Teacher
-
Syllabus
-
Institution
-
Study Program
-
Degree
-
LanguageEnglish
-
Tracks
ABSTRACT
The design of high-performance metamaterials and metastructures is a highly challenging problem from both the methodological and computational viewpoints due to the intrinsic complexity inherited from their multi-scale nature. Indeed, it often involves thousands of degrees-of-freedoms even for moderate-size devices composed by rather “simple” unit cells (UCs). Artificial Intelligence (AI) is a powerful tool to develop accurate and efficient surrogate models for predicting the response of a system as a function of both its material/geometric descriptors and the external excitation. This forms the foundation for developing efficient “digital twins” (DTs). The laboratory aims at providing the methodological skills and knowledge on efficient AI-driven design of metamaterials and metastructures through computer-guided examples.COURSE CONTENT
- Fundamentals of AI and Machine Learning (ML) algorithms
- ML as a "three-steps" process for building accurate DTs
- Dimensionality reduction and single-shot/adaptive sampling techniques
- Surrogate model for computational expensive metastructures and metamaterials
- System-by-Design (SbD) framework for the computationally-efficient design of complex multi-scale structures
- Applicative examples of AI-based metamaterials and metastructures designs
TEACHING ACTIVITIES
- Theoretical Lessons
- e-Xam Self Assessment (each teaching class or periodically)
- SW/HW Emulator Exercises
- e-Xam Final Assessment
FURTHER READINGS
- A. I. J. Forrester, A. Sobester, and A. J. Keane, Engineering Design via Surrogate Modelling: A Practical Guide. Hoboken, N.J.: John Wiley & Sons, 2008.
- T. Hastie, J. Friedman, and R. Tisbshirani, The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York: Springer, 2017.
- V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer, 2000.
- M. Z. Naser, Machine Learning for Civil & Environmental Engineers. Wiley, 2023.
- M. Li and M. Salucci, Eds., Applications of Deep Learning in Electromagnetics - Teaching Maxwell's Equations to Machines. London, United Kingdom: IET, 2022.
Course Information
Date: | 25 September – 26 September 2025 (15 hours) |
Format: | The course is offered on-site and on-line (synchronous and asynchronous) with video recordings, hand-outs, etc. of the lectures available off-line |
Registration Information
UniTN Students: | Free |
EXTERNAL Students: |
216 Eu: First course 180 Eu: Every course from the second one |
The fees include the course teaching, video recordings, hand-outs, etc. (*).
Registration Procedure for UniTN Students
Please contact the Student Support Office of your Department/Centre/School to include the course in your study plan.
Registration Procedure for EXTERNAL Students
Step 1: Register a "guest" type account (@guest.unitn.it)
- Should you still not have a UniTN account, you have to register and log in with your SPID identity or CIE (electronic ID card). If you cannot use SPID or CIE, please create your own UniTN account.
Step 2: Enroll to a Single UniTN Course
-
Complete the online application through the dedicated webpage.
In the application form (Section "Teaching Activities") put the following information:- Name of single class/teaching activity: Lab on AI-based Metamaterials & Metastructures Design
- Code of single class/teaching activity: M220_18
- Degree course to which the teaching activity is associated: [M220] Master in Multifunctional Metamaterials and Metastructures
- Once received the outcome of the application (1-3 days), login into ESSE3 with your "guest" account user-name and password. Then, pay the bulletin you find in Administrative Office – Payments.
NOTES:
- A vademecum with a step-by-step guide to enroll to a single course at the University of Trento is available here
- For any question on the registration process, please write to 2025.MAII.M3.UniTN.TRENTO.IT@unitn.it
(*) Each registered participant acknowledges that the material distributed in the frame of the course, available for the duration of one academic year, is protected by copyright and delivered for educational purposes and personal use only. The participant agrees and undertakes not to forward, publish, disclose, distribute, disseminate - in any form or manner - such a material without written consent of the author(s) of the material. Unless otherwise explicitly allowed by the speaker in written form, no recordings of the online lectures can be made.