System identification through Lipschitz regularized deep neural networks

DOI10.1016/j.jcp.2021.110549OpenAlexW3083490811MaRDI QIDQ2132640

Luca Capogna, Elisa Negrini, Giovanna Citti

Publication date: 28 April 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.03288

zbMATH Keywords

system identificationordinary differential equationsmachine learningdeep learninggeneralization gapregularized network

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Partial differential equations of mathematical physics and other areas of application (35Qxx) Model systems in control theory (93Cxx)

Related Items (2)

Optimal Transport for Parameter Identification of Chaotic Dynamics via Invariant Measures ⋮ Bayesian spatiotemporal modeling for inverse problems

Uses Software

• SciPy
• Python
• PyTorch

Cites Work

• Unnamed Item
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Robustness and generalization
• Frequency domain identification of continuous-time output error models. I: Uniformly sampled data and frequency function approximation
• Neural networks and dynamical systems
• Machine learning of linear differential equations using Gaussian processes
• Hidden physics models: machine learning of nonlinear partial differential equations
• Applied Koopman theory for partial differential equations and data-driven modeling of spatio-temporal systems
• On robust computation of Koopman operator and prediction in random dynamical systems
• Regularisation of neural networks by enforcing Lipschitz continuity
• Data-driven discovery of PDEs in complex datasets
• Data driven governing equations approximation using deep neural networks
• Nonlinear System Identification
• Applied Koopmanism
• Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• A fully automated recurrent neural network for unknown dynamic system identification and control
• Anomaly Detection and Classification for Streaming Data using PDEs
• Learning partial differential equations via data discovery and sparse optimization
• Nonlinear System Identification
• Sparse dynamics for partial differential equations
• Data-driven discovery of coordinates and governing equations
• Approximation by superpositions of a sigmoidal function

This page was built for publication: System identification through Lipschitz regularized deep neural networks