| 基于二重积分定义的神经网络求解数值积分模型及学习算法 |
| |
| 引用本文： | 蒋群华,周永权.基于二重积分定义的神经网络求解数值积分模型及学习算法[J].广西科学,2008,15(3):278-281. |
| |
| 作者姓名： | 蒋群华 周永权 |
| |
| 作者单位： | 广西发族大学数学与计算机科学学院,广西南宁,530006;广西发族大学数学与计算机科学学院,广西南宁,530006 |
| |
| 基金项目： | 国家自然科学基金，广西自然科学基金，广西民族大学重大项目 |
| |
| 摘 要： | 根据二重积分的定义和一般网络的拓扑结构特点,提出求解二重积分的神经网络模型和学习算法,并进行算法收敛性分析和算例验证.该算法收敛并且比传统的数值积分方法的计算精度高、收敛速度快.
|
| 关 键 词： | 神经网络 二重积分 数值积分 收敛性 |
| 收稿时间： | 2007/11/14 0:00:00 |
| 修稿时间： | 2007/12/24 0:00:00 |
The Model and Algorithm for Solving Numerical Integration Based on Double Integral Definition Neural Network |
| |
| JIANG Qun-hua and ZHOU Yong-quan.The Model and Algorithm for Solving Numerical Integration Based on Double Integral Definition Neural Network[J].Guangxi Sciences,2008,15(3):278-281. |
| |
| Authors: | JIANG Qun-hua and ZHOU Yong-quan |
| |
| Institution: | College of Mathematics and Computer Science, Guangxi University for Nationalities, Nanning, Guangxi, 530006, China and College of Mathematics and Computer Science, Guangxi University for Nationalities, Nanning, Guangxi, 530006, China |
| |
| Abstract: | According to the double integral definition and the characteristic of common network topology,a network model and algorithm is proposed for the double integration in this paper,and the convergence is analyzed.Simulated result of the example indicates that the method has higher accuracy and faster convergence rate than the traditional methods for the double integration. |
| |
| Keywords: | neural network double integral numerical integration convergence |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《广西科学》浏览原始摘要信息 |
| 点击此处可从《广西科学》下载免费的PDF全文 |
