Title :
Two-dimensional feed-forward functionally expanded neural network
Author :
Panagopoulos, Spyros ; Soraghan, John J.
Author_Institution :
Dept. of Electron. & Electr. Eng., Univ. of Strathclyde, Glasgow, UK
Abstract :
This paper is concerned with the development of a two-dimensional feed-forward functionally expanded neural network (2D FFENN) surface modeler. New nonlinear surface basis functions are proposed for the network´s functional expansion. A network optimization technique based on an iterative function selection strategy is also described. Comparative simulation results for surface mappings generated by the 2D FFENN, Multi-layered Perceptron (MLP) and Radial Basis Function (RBF) architectures are presented.
Keywords :
multilayer perceptrons; optimisation; radial basis function networks; 2D FFENN surface modeler; MLP; RBF architecture; iterative function selection strategy; multilayered perceptron; network functional expansion; network optimization technique; nonlinear surface basis functions; radial basis function architecture; surface mappings; two-dimensional feed-forward functionally expanded neural network; Approximation methods; Biological neural networks; Computational modeling; Neurons; Radial basis function networks; Sea surface; Training;
Conference_Titel :
Signal Processing Conference, 2002 11th European
Conference_Location :
Toulouse
