| 并行协作模块化神经网络体系结构 |
| |
| 引用本文： | 凌卫新,郑启伦,陈琼,吕翠英.并行协作模块化神经网络体系结构[J].北京邮电大学学报,2002,25(2):14-17,51. |
| |
| 作者姓名： | 凌卫新 郑启伦 陈琼 吕翠英 |
| |
| 作者单位： | 1. 华南理工大学应用数学系,广州,510640;2. 华南理工大学计算机科学与工程学院,广州,510640 |
| |
| 基金项目： | 国家自然科学基金;69783008; |
| |
| 摘 要： | 提出了一种并行协作模块化神经网络的体系结构和学习算法,它可实现复杂任务的自动分解判定和模块化训练策略.实验表明,本文提出的体系结构和算法与非模块化神经网络技术相比,提高了训练速度、改善了网络性能,它具有高效并行运行效率、容易实现新增样本学习等特点.
|
| 关 键 词： | 神经网络 模块化结构 学习算法 分解判定 |
| 文章编号： | 1007-5321(2002)02-0014-04 |
A Modular Neural Network Architecture Based on Parallel Cooperation |
| |
| LING Wei-xin ,ZHENG Qi-lun ,CHEN Qiong ,LU Cui-ying.A Modular Neural Network Architecture Based on Parallel Cooperation[J].Journal of Beijing University of Posts and Telecommunications,2002,25(2):14-17,51. |
| |
| Authors: | LING Wei-xin ZHENG Qi-lun CHEN Qiong LU Cui-ying |
| |
| Affiliation: | LING Wei-xin 1,ZHENG Qi-lun 2,CHEN Qiong 2,LU Cui-ying 1 |
| |
| Abstract: | The architecture and algorithm of Parallel Cooperative Modular Neural Network (PCMNN) are proposed in this paper. It has the advantage of automatic decomposition of given task and its modular training of network. Experiments proposed in this paper is practicable and effective and is superior to non-modular method due to its high efficiency for a parallel network system structure, easy implementation of additional learning and modular structure for implementation by hardware. |
| |
| Keywords: | neural network modular structure learning algorithm decomposition decision |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
