## Abstract

Artificial neural networks (ANNs) are often used for short term discrete time series predictions. Continuous-time models are, however, required for qualitatively correct approximations to long-term dynamics (attractors) of nonlinear dynamical systems and their transitions (bifurcations) as system parameters are varied. In previous work we developed a black-box methodology for the characterization of experimental time series as continuous-time models (sets of ordinary differential equations) based on a neural network platform. This methodology naturally lends itself to the identification of partially known first principles dynamic models, and here we present its extension to `gray-box' identification.

Original language | English (US) |
---|---|

Pages | 596-605 |

Number of pages | 10 |

State | Published - 1994 |

Event | Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) - Ermioni, GREECE Duration: Sep 6 1994 → Sep 8 1994 |

### Other

Other | Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) |
---|---|

City | Ermioni, GREECE |

Period | 9/6/94 → 9/8/94 |

## All Science Journal Classification (ASJC) codes

- Signal Processing
- Software
- Electrical and Electronic Engineering