Learning Dissipative Neural Dynamical Systems

arXiv:2309.16032v2 Announce Type: replace
Abstract: Consider an unknown nonlinear dynamical system that is known to be dissipative. The objective of this paper is to learn a neural dynamical model that approximates this system, while preserving the dissipativity property in the model. In general, imposing dissipativity constraints during neural network training is a hard problem for which no known techniques exist. In this work, we address the problem of learning a dissipative neural dynamical system model in two stages. First, we …

abstract arxiv constraints cs.lg cs.sy eess.sy general learn math.ds math.oc network network training neural network paper property systems training type