多层前馈式神经网络的HJPS训练算法

根据优化理论中的Hooke—Jeeves模式搜索（pattern search）法提出了多层前馈式神经网络快速训练算法HJPS．该算法由“探测搜索”和“模式移动”两个步骤交替进行．其基本思想是探测搜索依次沿各个坐标轴进行，用以确定新的基点和有利于网络误差函数值下降的方向．模式移动沿相邻两个基点的连线方向前进，从而进一步减小误差函数值，达到更快收敛．实验结果表明，同BP算法以及其他几种快速算法相比，HJPS算法在收敛速度和运算时间上都有非常显著的提高．同时HIPS算法的泛化能力很强．

The HJPS Training Algorithm for Multilayer Feedforward Neural Networks

Based on the Hooke-Jeeves pattern search method of optimization theory, a fast training algorithm, HJPS, is proposed for multilayer feedforward neural networks in this paper. It consists of two alternating steps: exploratory search and pattern move. In the training process, only the changed part of the error functio n is considered. The results of simulations, including a function approximation problems and a pattern recognition problem, show that the propounded algorithm is remarkably improved compared with BP and other faster algorithms in terms of converging speed and computing time. The high generalization ability of HJPS al gorithm is also demonstrated by the experimental results.