节点文献
基于微分进化免疫的RBF网络学习算法研究
Research on RBF Network Leaning Method Based on Differential Immunity
【摘要】 该文提出一种微分进化算法与免疫算法相结合的方法,将该方法用于优化RBF网络隐节点参数,以改进RBF网络的性能,仿真结果表明收敛速度较快,训练精度较高,有效地改进网络的泛化能力.
【Abstract】 The paper presents a hybrid algorithm which is combined by differential evolution and immune algorithm,It is used for optimizing parameter of RBF network and improving function of RBF network.The result of experiment means the convergent speed is quickly and training accuracy is higher,improve generalization ability of a network.
【关键词】 微分进化;
免疫算法;
径向基神经网络;
非线性时间序列;
【Key words】 differential evolution; immunity algorithm; RBF; nonlinear time-series;
【Key words】 differential evolution; immunity algorithm; RBF; nonlinear time-series;
【基金】 国家自然科学基金(60572074)资助项目
- 【文献出处】 江西师范大学学报(自然科学版) ,Journal of Jiangxi Normal University(Natural Sciences Edition) , 编辑部邮箱 ,2008年01期
- 【分类号】TP183
- 【被引频次】4
- 【下载频次】123