This work analyses the problems related to the reconstruction of a dynamical system, which exhibits chaotic behaviour, from time series associated with a single observable of the system itself, by using feedforward neural network model. The starting network architecture is obtained setting the number of input neurons according to the Takens' theorem, and then is imporved by slightly increasing the number of inputs. The choice of the number of the hidden neurons is based on the results obtained testing different net structures. The effectiveness of the method is demonstrated by applying it to the Brusselator system (Phys. Lett. 91 (1982) 263). (C) 2003 Elsevier B.V. All rights reserved.
Reconstruction of chaotic time series by neural models: a case study / Stefania, Tronci; Giona, Massimiliano; Roberto, Baratti. - In: NEUROCOMPUTING. - ISSN 0925-2312. - 55:3-4(2003), pp. 581-591. (Intervento presentato al convegno 7th International Conference on Engineering Application of Neural Networks tenutosi a CAGLIARI, ITALY nel JUL, 2001) [10.1016/s0925-2312(03)00394-1].
Reconstruction of chaotic time series by neural models: a case study
GIONA, Massimiliano;
2003
Abstract
This work analyses the problems related to the reconstruction of a dynamical system, which exhibits chaotic behaviour, from time series associated with a single observable of the system itself, by using feedforward neural network model. The starting network architecture is obtained setting the number of input neurons according to the Takens' theorem, and then is imporved by slightly increasing the number of inputs. The choice of the number of the hidden neurons is based on the results obtained testing different net structures. The effectiveness of the method is demonstrated by applying it to the Brusselator system (Phys. Lett. 91 (1982) 263). (C) 2003 Elsevier B.V. All rights reserved.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
