Abstract
A new approximating sensitivity algorithm in prediction error method is derived for a class continuous nonlinear dynamic system identification including training multi-layer neural networks. The algorithm can be used to approximate the gradient of output with respect to unknown parameter in a wic class of continuous-discrete nonlinear systems. The comparison between new and convention algorithm, and simulated example is included to demonstrate the effectiveness of the new algorithm.
Original language | English |
---|---|
Pages (from-to) | 45-58 |
Number of pages | 14 |
Journal | Advances in Modelling and Analysis B |
Volume | 44 |
Issue number | 3-4 |
Publication status | Published - 2001 |
Externally published | Yes |
Keywords
- Approximating sensitivity
- Continuous nonlinear system
- Neural networks
- Prediction error