| 基于遗传算法的神经网络集成在人耳识别中的应用 |
| |
| 引用本文： | 陈春兰,曾黄麟,许立志.基于遗传算法的神经网络集成在人耳识别中的应用[J].现代电子技术,2010,33(8):148-150. |
| |
| 作者姓名： | 陈春兰 曾黄麟 许立志 |
| |
| 作者单位： | 1. 泸州职业技术学院,四川,泸州,646005
2. 四川理工学院,四川,自贡,643000 |
| |
| 摘 要： | BP神经网络算法存在收敛速度慢和网络泛化能力差的缺点，影响分类识别率。为了提高网络的分类识别能力和泛化能力，在此介绍一种基于遗传算法的神经网络集成方法，即训练出多个个体BP神经网络，利用遗传算法选择差异度较大的个体BP网络进行神经网络集成，再利用该神经网络集成进行分类识别。实验结果表明，神经网络集成可以提高识别率。
|
| 关 键 词： | BP神经网络 遗传算法 神经网络集成 人耳识别 |
Application of Neural Network Ensemble Based on Genetic Algorithm in Ear Recognition |
| |
| CHEN Chun-lan,ZENG Huang-lin,XU Li-zhi.Application of Neural Network Ensemble Based on Genetic Algorithm in Ear Recognition[J].Modern Electronic Technique,2010,33(8):148-150. |
| |
| Authors: | CHEN Chun-lan ZENG Huang-lin XU Li-zhi |
| |
| Affiliation: | CHEN Chun-lan1,ZENG Huang-lin2,XU Li-zhi2 (1.Luzhou Vocational , Technical College,Luzhou 646005,China,2.Sichuan University of Science & Engineering,Zigong 643000,China) |
| |
| Abstract: | Since the constringency of the BP neural network algorithm is too slow and generalization capability of neural network is not ideal,the disadvantages effect the classification identification.A method of the neural network ensemble based on the genetic algorithm is introduced for improving the classification accuracy and generalization of neural network,the way which trains several individual BP neural networks,selects those who have great variance each other to perform the neural network ensemble by means o... |
| |
| Keywords: | BP neural network genetic algorithm neural network ensemble ear recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
