Volterra Feedforward Neural Networks:Theory and Algorithms  

作　　者：Jiao Lichengl Liu Fang & Xie Qin(National Lab. for Radar Signal Processing and Center for Neural Networks,Xidian University, Xian 710071, P.R.China) 

出　　处：《Journal of Systems Engineering and Electronics》1996年第4期1-12,共12页系统工程与电子技术（英文版）

摘　　要：The Volterra feedforward neural network with nonlinear interconnections and related homotopy learning algorithm are proposed in the paper. It is shown that Volterra neural network and the homolopy learning algorithms are significant potentials in nonlinear approximation ability,convergent speeds and global optimization than the classical neural networks and the standard BP algorithm, and related computer simulations and theoretical analysis are given too.The Volterra feedforward neural network with nonlinear interconnections and related homotopy learning algorithm are proposed in the paper. It is shown that Volterra neural network and the homolopy learning algorithms are significant potentials in nonlinear approximation ability,convergent speeds and global optimization than the classical neural networks and the standard BP algorithm, and related computer simulations and theoretical analysis are given too.

关 键 词：Volterra neural networks Homotopy learning algorithm. 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]