| 一种多模块协同参与的神经网络 |
| |
| 引用本文： | 薄迎春,乔俊飞,杨刚.一种多模块协同参与的神经网络[J].智能系统学报,2011,6(3):225-230. |
| |
| 作者姓名： | 薄迎春 乔俊飞 杨刚 |
| |
| 作者单位： | 北京工业大学 电子信息与控制工程学院,北京,100124 |
| |
| 基金项目： | 国家自然科学基金资助项目，北京市自然科学基金资助项目，教育部博士点基金资助项目，北京市属高等学校人才强教计划资助项目 |
| |
| 摘 要： | 针对单一神经网络训练时间长、对复杂问题处理精度较低、易陷入局部极小等问题,提出了一种多模块协同参与信息处理的神经网络.该神经网络具有层级结构,基于条件模糊聚类技术对样本进行分类,根据分类结果实现对神经网络的模块划分,采用代数算法对网络权值进行求解,基于距离测度设计了处理输入信息的子网络选择方法.为提高神经网络对复杂问题的逼近能力,选择数目不等的多个子网络参与给定输入的协同处理,采取"分而治之"与"集成学习"相结合方法以提高网络的性能.实验表明,对于复杂问题,这种多模块协同参与的神经网络可以有效地提高网络的逼近精度,训练时间也优于单一网络.
|
| 关 键 词： | 神经网络 条件模糊聚类 多模块 子网络选择 |
A multi-module cooperative neural network |
| |
| BO Yingchun,QIAO Junfei,YANG Gang.A multi-module cooperative neural network[J].CAAL Transactions on Intelligent Systems,2011,6(3):225-230. |
| |
| Authors: | BO Yingchun QIAO Junfei YANG Gang |
| |
| Affiliation: | BO Yingchun,QIAO Junfei,YANG Gang (College of Electronic Information and Control Engineering,Beijing University of Technology,Beijing 100124,China) |
| |
| Abstract: | Aiming to solve the problems of long training time,low precision in processing complex problem,and a local minimum in single neural networks,a multi-module cooperative neural network(MMCNN) was proposed.Its structure has hierarchical character.Sample data was first detached by the fuzzy clustering method,and then the neural network was partitioned into several sub-nets based on the clustering results.The linking weights were elicited by solving equations.For a given input data,some multi-modules were select... |
| |
| Keywords: | neural networks conditional fuzzy clustering method multi-modules sub-nets selection |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
