%0 Journal Article
%T Combined algorithms for training RBF neural networks based on genetic algorithms and gradient descent<br>基于遗传算法和梯度下降的RBF神经网络组合训练方法
%A JIANG Peng-fei
%A CAI Zhi-hua
%A <br>姜鹏飞
%A 蔡之华
%J 计算机应用
%D 2007
%I 
%X The deficiencies of gradient descent method include the slow speed of convergence, the problem of local minima and the great influence of initial parameters on the performance of the network. Genetic Algorithm (GA) based methods can get rid of the problem of local optima, but they are not very effective to refine an existent good solution. For resolving these problems, in this paper we proposed a new algorithm. The experimental results show the algorithm performs well, and it is better than both Gradient descent algorithm and genetic algorithm.
%K Radial Basis Function (RBF) neural networks
%K genetic algorithms
%K gradient descent<br>径向基函数神经网络
%K 遗传算法
%K 梯度下降
%K 基于遗传算法
%K 梯度下降
%K 神经
%K 网络组合
%K 训练方法
%K gradient
%K descent
%K genetic
%K algorithms
%K based
%K RBF
%K neural
%K networks
%K training
%K 比较
%K 结果影响
%K 仿真实验
%K 数据集
%K 算法特点
%K 研究
%K 训练效果
%K 搜索能力
%K 最优
%K 问题
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=14E16CBD27430512BB3AF447E500F425&yid=A732AF04DDA03BB3&vid=DB817633AA4F79B9&iid=0B39A22176CE99FB&sid=2E41258BCB9A7DB2&eid=869B6F3117981EC4&journal_id=1001-9081&journal_name=计算机应用&referenced_num=11&reference_num=10