Teaching

This page collects courses and educational material from the Neu4mes group.

PhD course: Physics-Informed Machine Learning

A 5-day PhD course on combining physics with machine learning, with applications to robotics and autonomous systems.

Motivation and overview

Why combine physics with machine learning? The course introduces the motivation behind Physics-Informed Machine Learning, presents real-world applications in robotics and autonomous systems, outlines the overall structure of the programme, and explores physics-guided learning methods.

Topics covered:

• Physics-informed learning paradigms
• Physics-guided features and datasets
• Physics-encoded learning architectures
• Model-structured neural networks (MSNN)
• Hands-on tutorials with the nnodely framework
• Applications to modeling, planning, control, and state estimation of physical systems

Watch the course

Watch the full course on YouTube: Physics-Informed Machine Learning playlist.

Slides

Course slides (PDF):

• Introduction
• Physics-guided inputs
• Physics-informed loss
• Physics-encoded architectures — Part I
• Physics-encoded architectures — Part II
• Physics-encoded architectures — Part III
• nnodely and applications
• Outlook and future directions

Lecturers

• Dr. Mattia Piccinini (Technical University of Munich)
• Prof. Gastone Pietro Rosati Papini (University of Trento)