Abstract
The paper describes an improved version of the Radial Basis Function algorithm, which integrates the advantages of Multi-Layer Perceptrons and Radial Basis Functions alone. The proposed paradigm is more general in nature, since it has the other two as particular subcases. It finds applications in several pattern recognition and classification tasks. Furthermore it can also be used as a method to map Fuzzy Inference Systems on Artificial Neural Networks.
Similar content being viewed by others
References
P.D. Wasserman.Neural computing: theory and practice, Van Nostrand Reinhold, New York, 1989.
P.D. Wasserman.Advanced methods in neural computing, Van Nostrand Reinhold, New York, 1989.
D.A. White, D.A. Sofge.Handbook of intelligent control, Van Nostrand Reinhold, New York, 1992.
B. Lazzerini, F. Marcelloni, L.M. Reyneri, E. Rossi, L. Schiuma. II sistema BEATRIX per il Riconoscimento Automatico di Testi Manoscritti,Proc. of AICA 94, Palermo, pp. 1303–1318, September 1994.
L.W. Cough IIDigital and analog communication systems, Maxwell MacMillan International Editions, New York, 1989.
L.M. Reyneri, M. Chiaberge, L. Zocca. CINTIA: a neuro-fuzzy real-time controller for low power embedded systems,Proc. of Microneuro 94, Torino, IEEE Computer Society Press, pp. 392–404, September 1994.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Reyneri, L.M. Weighted Radial Basis Functions for improved pattern recognition and signal processing. Neural Process Lett 2, 2–6 (1995). https://doi.org/10.1007/BF02311571
Issue Date:
DOI: https://doi.org/10.1007/BF02311571