Modelling dynamic processes with clustered time-delay neurons

Neumerkel, D., Murray-Smith, R. and Gollee, H. (1993) Modelling dynamic processes with clustered time-delay neurons. In: IJCNN '93: Proceedings of the International Joint Conference on Neural Networks, 25-29 October 1993, Nagoya, Japan. IEEE Computer Society: Piscataway, N.J., USA, pp. 1765-1768. ISBN 9780780314221 (doi: 10.1109/IJCNN.1993.716995)

Full text not currently available from Enlighten.


This paper investigates the modelling capabilities of neural nets for a dynamic nonlinear process. Different neural structures are compared: multilayer perceptron (MLP) and radial basis function network (RBF) with an external tapped delay line, and modifications of both network types using internal delays, called time-delay MLP (TDMLP) and time-delay RBF (TDRBF). The nonlinear process to be modelled is a drive system including some nonlinearities, e.g. saturation effects. A special clustering procedure is introduced in order to increase the modelling accuracy, reduce computation and provide better generalisation.

Item Type:Book Sections
Glasgow Author(s) Enlighten ID:Murray-Smith, Professor Roderick and Gollee, Dr Henrik
Authors: Neumerkel, D., Murray-Smith, R., and Gollee, H.
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
College/School:College of Science and Engineering > School of Computing Science
College of Science and Engineering > School of Engineering > Biomedical Engineering
Publisher:IEEE Computer Society

University Staff: Request a correction | Enlighten Editors: Update this record