HomPINNs : homotopy physics-informed neural networks for solving the inverse problems of nonlinear differential equations with multiple solutions

Due to the complex behavior arising from non-uniqueness, symmetry, and bifurcations in the solution space, solving inverse problems of nonlinear differential equations (DEs) with multiple solutions is a challenging task. To address this, we propose homotopy physics-informed neural networks (HomPINNs...

Description complète

Détails bibliographiques

Publié dans:	Journal of computational physics. - 1986. - 500(2024) vom: 01. März
Auteur principal:	Zheng, Haoyang (Auteur)
Autres auteurs:	Huang, Yao, Huang, Ziyang, Hao, Wenrui, Lin, Guang
Format:	Article en ligne
Langue:	English
Publié:	2024
Accès à la collection:	Journal of computational physics
Sujets:	Journal Article Homotopy continuation method Machine learning Multiple solutions Nonlinear differential equations Physics-informed neural networks