全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

椭球基函数神经网络的混合学习算法*

, PP. 148-154

Keywords: 椭球基函数神经网络(EBFNN),混合学习算法,全协方差矩阵,椭球基函数

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出一种训练椭球基函数神经网络(EBFNN)的混合学习算法.此算法首先使用期望最大化算法初始化EBFNN中椭球基函数节点的参数,而网络的连接权重和偏差项则用线性最小二乘方法进行初始化.然后用梯度下降法对EBFNN中所有参数同时进行优化.与其他3个相关的模型相比,用混合学习方法训练的梯度下降椭球基函数神经网络(GDEBFNN)能够取得更优的分类性能.此外,与支持向量机对比表明,GDEBFNN取得与之接近的泛化能力.与基于Adaboost的决策树模型比较表明,GDEBFNN可以取得更优的泛化性能.

References

[1]  Haykin S. Neural Networks: A Comprehensive Foundation. 2nd Edition. New York, USA: Prentice Hall, 1999
[2]  Lampriello F, Sciandrone M. Efficient Training of RBF Neural Networks for Pattern Recognition. IEEE Trans on Neural Networks, 2001, 12(5): 12351242
[3]  Wedding D K, Cios K J. Time Series Forecasting by Combining RBF Networks, Certainty Factors, and the BoxJenkins Model. Neurocomputing, 1996, 10(2): 149168
[4]  VakilBaghmisheh M T, Pavesic N. Training RBF Networks with Selective Backpropagation. Neurocomputing, 2004, 62(1): 3964
[5]  Karayiannis N B. Reformulated Radial Basis Neural Networks Trained by Gradient Descent. IEEE Trans on Neural Networks, 1999, 10(3): 657671
[6]  Xiao Di, Hu Shousong. Ellipsoidal Basis Functional Neural Network Based on Rough KMeans. Journal of Nanjing University of Aeronautics & Astronautics, 2006, 38(3): 321325 (in Chinese) (肖 迪,胡寿松.一种基于粗糙K均值的椭球基函数神经网络. 南京航空航天大学学报, 2006, 38(3): 321325)
[7]  Mak M W, Kung S Y. Estimation of Elliptical Basis Function Parameters by the EM Algorithm with Application to Speaker Verification. IEEE Trans on Neural Networks, 2000, 11(4): 961969
[8]  Zhao Xiang, Zhou Shaoqi, Xiao Deyun. Improved Ellipsoidal Unit Neural Networks and Its Applications in CSTR. Journal of Chongqing University: Natural Science Edition, 2002, 25(5): 5863 (in Chinese) (赵 翔,周绍琦,萧德云.改进的椭球单元网络及其在故障诊断中的应用.重庆大学学报:自然科学版, 2002, 25(5): 5863)
[9]  Luo Jiancheng, Chen Qiuxian, Zheng Jiang, et al. An Elliptical Basis Function Network for Classification of RemoteSensing Images // Proc of the IEEE International Symposium on Geoscience and Remote Sensing. Toulouse, France, 2003, Ⅵ: 34893494
[10]  Yiu K K, Mak M W, Li C K. Gaussian Mixture Models and Probabilistic DecisionBased Neural Networks for Pattern Classification: A Comparative Study. Neural Computing & Applications, 1999, 8(3): 235245
[11]  Blake C, Merz C. UCI Repository of Machine Learning Datasets [DB/OL]. [19980101]. http://www.ics.uci.edu/~mlearn/MLRepository.html
[12]  Vapnik V N. The Nature of Statistical Learning Theory. New York, USA: SpringerVerlag, 1995

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133