| 广义多项式神经网络及其结构自适应确定 |
| |
| 引用本文： | 肖秀春,姜孝华,张雨浓.广义多项式神经网络及其结构自适应确定[J].重庆工学院学报,2009,23(7):97-99. |
| |
| 作者姓名： | 肖秀春 姜孝华 张雨浓 |
| |
| 作者单位： | 广东海洋大学信息学院;中山大学信息科学与技术学院;浙江大学CAD/CG国家重点实验室; |
| |
| 基金项目： | 国家自然科学基金资助项目(60775050);;浙江大学CAD/CG国家重点实验室开放课题资助项目(A0908) |
| |
| 摘 要： | 在前向神经网络模型的基础上,构建了一类新型广义多项式神经网络,依据BP神经网络梯度下降法的思想,给出该神经网络的权值迭代修正公式,并在此基础上建立其结构自适应确定算法,并进行仿真实验.结果表明,该神经网络计算精度高、能自适应地确定网络结构.
|
| 关 键 词： | 广义多项式 神经网络 结构自适应确定 |
General Polynomial Neural Network and Its Structure Adaptive Determination |
| |
| XIAO Xiu-chun,,JIANG Xiao-hua,ZHANG Yu-nong.General Polynomial Neural Network and Its Structure Adaptive Determination[J].Journal of Chongqing Institute of Technology,2009,23(7):97-99. |
| |
| Authors: | XIAO Xiu-chun JIANG Xiao-hua ZHANG Yu-nong |
| |
| Affiliation: | 1.College of Information;Guangdong Ocean University;Zhanjiang 524088;China;2.School of Information Science and Technology;Sun Yat-sen University;Guangzhou 510275;3.State Key Lab of CAD&CG;Zhejiang University;Hangzhou 310058;China |
| |
| Abstract: | In this paper,based on special feed-forward neural network,a novel type of general polynomial neural network is constructed.According to the idea of the declining of gradient of BP neural network,the weight iterative modification formula of this neural network is presented.Accordingly,a structure-adaptive-determination method is proposed and its simulation experiemnts are conducted.Theoretical analysis and simulation results substantiate that such a neural network could be efficient and accurate and determi... |
| |
| Keywords: | general polynomial neural network structure-adaptive-determination |
| 本文献已被 CNKI 维普 等数据库收录！ |
