Title :
Sequentially adaptive neural networks
Author :
Kadirkamanathan, V. ; Fallside, F.
Author_Institution :
Dept. of Eng., Cambridge Univ., UK
Abstract :
A sequential adaptation scheme for neural networks is proposed. The scheme is formulated as equality constrained optimization tasks. The approach taken in developing the scheme is based on the geometric point of view of pattern recognition and on methods of surface interpolation. The set of training equations for the radial basis function network of Gaussian nodes is developed, and an experiment on its classification performance is carried out
Keywords :
interpolation; neural nets; optimisation; pattern recognition; Gaussian nodes; classification performance; equality constrained optimization; pattern recognition; radial basis function network; surface interpolation; training equations; Adaptive systems; Biological neural networks; Constraint optimization; Equations; Interpolation; Kernel; Multilayer perceptrons; Neural networks; Pattern recognition; Training data;
Conference_Titel :
TENCON '89. Fourth IEEE Region 10 International Conference
Conference_Location :
Bombay
DOI :
10.1109/TENCON.1989.176912
