Training of parameters and time delays of universal learning network with switching mechanism
HAN Min
XI Jian-hui
HIRASAWA Kotaro
Abstract：A new modeling method using the ULN with switching mechanism is studied, where both parameters and time delays are adjusted to model the nonlinear systems. The simulation results of nonlinear system identification problems show that better performances can be obtained by the proposed method than the conventional method using only the parameter optimization. And how the generalization ability of modeling dynamic systems is influenced by the network size is also studied using the ULN with switching mechanism.
Keywords：universal learning networkrandom searchtime delaysneural networkgeneralization ability
Publication Date：2003-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 205-210 )