Weak Form Generalized Hamiltonian Learning

Autor: Course, Kevin L., Evans, Trefor W., Nair, Prasanth B.
Rok vydání: 2021
Předmět:
Zdroj: Advances in Neural Information Processing Systems. Vol. 33 (2020), pp. 18716-18726
Druh dokumentu: Working Paper
Popis: We present a method for learning generalized Hamiltonian decompositions of ordinary differential equations given a set of noisy time series measurements. Our method simultaneously learns a continuous time model and a scalar energy function for a general dynamical system. Learning predictive models in this form allows one to place strong, high-level, physics inspired priors onto the form of the learnt governing equations for general dynamical systems. Moreover, having shown how our method extends and unifies some previous work in deep learning with physics inspired priors, we present a novel method for learning continuous time models from the weak form of the governing equations which is less computationally taxing than standard adjoint methods.
Comment: 34th Conference on Neural Information Processing Systems, 18 pages
Databáze: arXiv