LR-RaNN: Lipschitz Regularized Randomized Neural Networks for System Identification

Chunyang Liao

Track: Full Paper (8 pages)

Keywords: System Identification, Randomized Neural Networks, Lipschitz Regularization

Abstract: Approximating the governing equations from data is of great importance in studying the dynamical systems. In this paper, we propose randomized neural networks (RaNN) to investigate the problem of approximating the governing equations of the system of ordinary differential equations. In contrast with other neural networks based methods, training randomized neural network solves a least-squares problem, which significant reduces the computational complexity. Moreover, we introduce a regularization term to the loss function, which improves the generalization ability. We provide an estimation of Lipschitz constant for our proposed model and analyze its generalization error. Our empirical experiments on synthetic datasets demonstrate that our proposed method achieves good generalization performance and enjoys easy implementation.

Submission Number: 1