Linearly Recurrent Autoencoder Networks for Learning Dynamics
| Autor: | Samuel E. Otto, Clarence W. Rowley |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
High dimensional systems
Mathematics::Dynamical Systems Artificial neural network Computer science Topology 01 natural sciences Autoencoder 010305 fluids & plasmas Nonlinear dynamical systems Nonlinear system Operator (computer programming) Modeling and Simulation Learning dynamics 0103 physical sciences Analysis |
| Zdroj: | SIAM Journal on Applied Dynamical Systems. 18:558-593 |
| ISSN: | 1536-0040 |
| Popis: | This paper describes a method for learning low-dimensional approximations of nonlinear dynamical systems, based on neural network approximations of the underlying Koopman operator. Extended Dynamic... |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|