摘要
基于神经网络间的差异性,提出一种选择性神经网络集成方法.该方法利用差异性度量,选择满足一定条件的个体神经网络组成神经网络集成,选出的个体神经网络既满足个体的精度要求,又满足个体神经网络之间的差异性要求.理论分析和实验结果表明,利用该方法能够提高神经网络集成的分类识别率.
Based on the diversity between neural networks, a method for neural network ensemble is proposed. Using diversity measure, this method selects some individual neural networks which satisfies specify conditions, and then these individual neural networks constitute neural networks ensemble. The individual networks selected satisfy both individual accuracy and diversity. Theoretical analysis and experimental results show that using this method can improve the accuracy of pattern classification.
出处
《扬州大学学报(自然科学版)》
CAS
CSCD
2007年第2期47-49,共3页
Journal of Yangzhou University:Natural Science Edition
基金
国家自然科学基金(60074013)
扬州大学科研基金(KK0413160)
关键词
差异性度量
选择性集成
模式分类
diversity measure
selective ensemble
pattern classification