caa a22 4500 475833961 CHVBK 20180406123849.0 cr unu---uuuuu 170329e20001001xx s 000 0 eng 10.1007/s005210070012 doi (NATIONALLICENCE)springer-10.1007/s005210070012 Automated Recurrent Neural Network Design to Model the Dynamics of Complex Systems [Elektronische Daten] [R. Baratti, B. Cannas, A. Fanni, F. Pilo] A general purpose implementation of the tabu search metaheuristic, called Universal Tabu Search, is used to optimally design a locally recurrent neural network architecture. The design of a neural network is a tedious and time consuming trial and error operation that leads to structures whose optimality is not guaranteed. In this paper, the problem of choosing the number of hidden neurons and the number of taps and delays in the FIR and IIR network synapses is formalised as an optimisation problem, whose cost function to be minimised is the network error calculated on a validation data set. The performance of the proposed approach has been tested on the problem of modelling the dynamics of a non-isothermal, continuously stirred tank reactor, in two different operating conditions: when a first order exothermic reaction is occurring; and when two consecutive first order reactions lead to a chaotic behaviour. Comparisons with alternative neural approaches are reported, showing the usefulness of the proposed method.: Springer-Verlag London Limited, 2000 Keywords: Automatic neural network design nationallicence Chaotic systems nationallicence Chemical reactors nationallicence Recurrent neural networks nationallicence Tabu search nationallicence Time series forecasting nationallicence Baratti R. Department of Chemical Engineering and Material Science, University of Cagliari, Cagliari, Italy, IT aut Cannas B. Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy, IT aut Fanni A. Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy, IT aut Pilo F. Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy, IT aut https://doi.org/10.1007/s005210070012 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s005210070012 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Baratti R. Department of Chemical Engineering and Material Science, University of Cagliari, Cagliari, Italy, IT aut NATIONALLICENCE 700 1- Cannas B. Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy, IT aut NATIONALLICENCE 700 1- Fanni A. Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy, IT aut NATIONALLICENCE 700 1- Pilo F. Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy, IT aut Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer