Research project
Lagrangian Neural Networks and Symbolic Regression
Implementing physics-informed neural networks to learn theoretical quantities like the Lagrangian from trajectory data using symbolic regression
This project was conducted as undergraduate research (PHYS492) at Boğaziçi University under the supervision of Asst. Prof. Arkadaş Özakın from February 2024 to June 2024.
Project Overview
This project implemented Lagrangian Neural Networks (LNNs) in PyTorch, combining physics principles with deep learning. I developed a tool using symbolic regression (PySR) to infer the mathematical form of Lagrangian from trajectory data.
The work explored theoretical concepts including Noether’s theorem and symplectic integrators, creating a bridge between classical mechanics and modern machine learning techniques.
The combination of neural networks with symbolic regression provided an interpretable route from observed trajectories to candidate analytical laws.
Useful links
Keywords
PyTorch · PySR · Symbolic Regression · Physics-Informed ML · Classical Mechanics