%0 Electronic Article
%A F.L. Chung
%A T. Lee
%K feedforward neural networks
%K network-growth approach
%K progressive-training algorithm
%K convergence
%K global minimum solution
%K hidden node
%K training patterns
%X A critical issue in applying the multilayer feedforward networks is the need to predetermine an appropriate network size for the problem being solved. A network-growth approach is pursued to address the problems concurrently and a progressive-training (PT) algorithm is proposed. The algorithm starts training with a one-hidden-node network and a one-pattern training subset. The training subset is then expanded by including one more pattern and the previously trained network, with or without a new hidden node grown, is trained again to cater for the new pattern. Such a process continues until all the available training patterns have been taken into account. At each training stage, convergence is guaranteed and at most one hidden node is added to the previously trained network. Thus the PT algorithm is guaranteed to converge to a finite-size network with a global minimum solution.
%@ 1350-2379
%T Network-growth approach to design of feedforward neural networks
%B IEE Proceedings - Control Theory and Applications
%D September 1995
%V 142
%N 5
%P 486-492
%I
%U https://digital-library.theiet.org/;jsessionid=dw5k2gcl4og6.x-iet-live-01content/journals/10.1049/ip-cta_19951969
%G EN