J4 ›› 2009, Vol. 27 ›› Issue (05): 514-.
• 论文 • 上一篇 下一篇
李春好1|刘成明1,才 淦2
出版日期:
发布日期:
通讯作者:
作者简介:
基金资助:
国家自然科学基金重点资助项目(70732005);国家自然科学基金资助项目(70471015)
LI Chun-hao1, LIU Cheng-ming1,CAI Gan2
Online:
Published:
摘要:
为有效剔除学习样本中的病态样本,以提高神经网络的泛化能力,提出一种新的病态样本搜索思想并应用海明距离,给出了基于搜索思想和海明距离的前馈神经网络病态样本剔除方法。该方法不用纳入专家的先验知识、样本形式等其他因素即可完成对病态样本的搜索和剔除,具有较强的适用性。数值模拟实验分析结果表明,该方法是一种科学、有效的方法,借助其能有效地搜索出学习样本中所存在的病态样本,对解决实际问题具有较大的应用价值。
关键词: 前馈神经网络, 病态样本, 剔除, 搜索, 海明距离
Abstract:
For efficiently eliminating morbid samples and improving the generalization ability of neural networks, we present an approach to eliminate morbid samples in forward neural networks based on the search thought and the Hamming distance, through developing the thought and introducing the distance. The approach can directly carry out searching and eliminating morbid samples, and do not consider prior knowledge, forms of samples, etc. Hence, its applicability is stronger. The results of numerical demonstration analysis show that the approach is scientific, effective and can effectively find out morbid samples of learning samples,it has obvious application value to solve problems of real world.
Key words: forward neural network, morbid sample, eliminate, search, hamming distance
中图分类号:
李春好|刘成明,才 淦. 前馈神经网络病态学习样本剔除方法[J]. J4, 2009, 27(05): 514-.
LI Chun-hao, LIU Cheng-ming,CAI Gan. Approach to Eliminating Morbid Samples in Forward Neural Networks[J]. J4, 2009, 27(05): 514-.
0 / / 推荐
导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks
链接本文: http://xuebao.jlu.edu.cn/xxb/CN/
http://xuebao.jlu.edu.cn/xxb/CN/Y2009/V27/I05/514
Cited