http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Xi, L.,Muzhou, H.,Lee, M.H.,Li, J.,Wei, D.,Hai, H.,Wu, Y. Elsevier Science, B.V 2014 Applied soft computing Vol.15 No.-
In this paper, in order to optimize neural network architecture and generalization, after analyzing the reasons of overfitting and poor generalization of the neural networks, we presented a class of constructive decay RBF neural networks to repair the singular value of a continuous function with finite number of jumping discontinuity points. We proved that a function with m jumping discontinuity points can be approximated by a simplest neural network and a decay RBF neural network in L<SUP>2</SUP>(@?) by each @? error, and a function with m jumping discontinuity point y=f(x),x@?E@?@?<SUP>d</SUP> can be constructively approximated by a decay RBF neural network in L<SUP>2</SUP>(@?<SUP>d</SUP>) by each ε>0 error. Then the whole networks will have less hidden neurons and well generalization in the same of the first part. A real world problem about stock closing price with jumping discontinuity have been presented and verified the correctness of the theory.