Nonlinear system identification employing automatic differentiation
arXiv:1507.02543 · doi:10.1016/j.cnsns.2013.02.017
Abstract
An optimization based state and parameter estimation method is presented where the required Jacobian matrix of the cost function is computed via automatic differentiation. Automatic differentiation evaluates the programming code of the cost function and provides exact values of the derivatives. In contrast to numerical differentiation it is not suffering from approximation errors and compared to symbolic differentiation it is more convenient to use, because no closed analytic expressions are required. Furthermore, we demonstrate how to generalize the parameter estimation scheme to delay differential equations, where estimating the delay time requires attention.
12 pages, 4 figures
References in corpus (7)
- Theory and computation of covariant Lyapunov vectors
- On Variational Data Assimilation in Continuous Time
- Using synchronization of chaos to identify the dynamics of unknown systems
- State and parameter estimation using Monte Carlo evaluation of path integrals
- Observers for canonic models of neural oscillators
- Sensitivity And Out-Of-Sample Error in Continuous Time Data Assimilation
- Effective Actions for Ensemble Data Assimilation