首页 | 本学科首页   官方微博 | 高级检索  
     

前馈网络泛化性能改进的目的规划方法研究
引用本文:胡铁松,沈佩君,郭元裕,万毅. 前馈网络泛化性能改进的目的规划方法研究[J]. 系统工程学报, 1997, 0(2)
作者姓名:胡铁松  沈佩君  郭元裕  万毅
作者单位:武汉水利电力大学,军事经济学院
基金项目:国家自然科学基金青年基金,中国博士后基金
摘    要:以目的规划模型为基础,将前馈网络准则函数改进、网络灵敏度降低、先验知识运用有机地结合在一起,提出了前馈网络泛化性能改进的目的规划方法.文中给出了该方法的数学模型、求解方法以及算例

关 键 词:前馈神经网络,泛化性能,目的规划

THE GOAL PROGRAMMING METHOD FOR IMPROVING GENERALIZATION PERFORMANCE OF THE FEEDFORWARD NEURAL NETWORKS
Hu Tiesong Shen Peijun Guo Yuanyu. THE GOAL PROGRAMMING METHOD FOR IMPROVING GENERALIZATION PERFORMANCE OF THE FEEDFORWARD NEURAL NETWORKS[J]. Journal of Systems Engineering, 1997, 0(2)
Authors:Hu Tiesong Shen Peijun Guo Yuanyu
Abstract:One of the important characteristic of feedforward neural networks is their ability to generalize the input/output behavior of functions based on a set of training examples.Yet many aspects of the problem of the improving generalization in feedforward neural networks have not been stuided well.The goal programmming method for neural network is proposed in this paper.Three enhancements are made in this method,those are:1)improvement of objective function;2)use of prior knowledge,3)decrease of the sensitivity of the neural network.Theoretical analysis and numerical example show that both generalization performance and the precision of forecasting of the neural networks are improved effectively.
Keywords:feedforward neural networks  generalization performance  goal programming  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号