Recurrent Neural Networks for Partially Observed Dynamical Systems
arXiv:2109.11629 · doi:10.1103/PhysRevE.105.044205
Abstract
Complex nonlinear dynamics are ubiquitous in many fields. Moreover, we rarely have access to all of the relevant state variables governing the dynamics. Delay embedding allows us, in principle, to account for unobserved state variables. Here we provide an algebraic approach to delay embedding that permits explicit approximation of error. We also provide the asymptotic dependence of the first order approximation error on the system size. More importantly, this formulation of delay embedding can be directly implemented using a Recurrent Neural Network (RNN). This observation expands the interpretability of both delay embedding and RNN and facilitates principled incorporation of structure and other constraints into these approaches.
arXiv comment11 pages, 5 figures
References in corpus (6)
- Deep learning for universal linear embeddings of nonlinear dynamics
- Data Driven Governing Equations Approximation Using Deep Neural Networks
- Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
- Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
- Multivariate phase space reconstruction by nearest neighbor embedding with different time delays
- Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't