Metalearning generalizable dynamics from trajectories
arXiv:2301.00957 · doi:10.1103/PhysRevLett.131.067301
Abstract
We present the interpretable meta neural ordinary differential equation (iMODE) method to rapidly learn generalizable (i.e., not parameter-specific) dynamics from trajectories of multiple dynamical systems that vary in their physical parameters. The iMODE method learns meta-knowledge, the functional variations of the force field of dynamical system instances without knowing the physical parameters, by adopting a bi-level optimization framework: an outer level capturing the common force field form among studied dynamical system instances and an inner level adapting to individual system instances. A priori physical knowledge can be conveniently embedded in the neural network architecture as inductive bias, such as conservative force field and Euclidean symmetry. With the learned meta-knowledge, iMODE can model an unseen system within seconds, and inversely reveal knowledge on the physical parameters of a system, or as a Neural Gauge to "measure" the physical parameters of an unseen system with observed trajectories. We test the validity of the iMODE method on bistable, double pendulum, Van der Pol, Slinky, and reaction-diffusion systems.
References in corpus (9)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
- Data-driven discovery of coordinates and governing equations
- Discovering physical concepts with neural networks
- AI Poincaré: Machine Learning Conservation Laws from Trajectories
- Machine-learning hidden symmetries
- Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems
- Cellular Sensing Governs the Stability of Chemotactic Fronts
- Rapidly Encoding Generalizable Dynamics in a Euclidean Symmetric Neural Network