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...

粗糙集约简的WNN隐层节点优化方法

DOI: 10.13195/j.kzyjc.2013.1029, PP. 1091-1096

Keywords: 小波神经网络,粗糙集,气动力建模

Full-Text   Cite this paper   Add to My Lib

Abstract:

在确保网络性能的前提下,如何确定最佳隐层节点,获得最简网络结构是小波神经网络(WNN)应用推广的关键.对此,引入粗糙集理论,提出了基于信息熵的卡方离散化算法和启发式的属性约简递归算法,利用粗糙集约简过程对WNN隐层节点进行精简,并将其应用于飞行器气动力建模.仿真结果表明,采用改进的粗糙集方法设计WNN,不仅能够简化网络结构,而且与未经结构优化的WNN相比,其模型精度和训练速度都得到了实质性改善.

References

[1]  张昭昭, 乔俊飞, 杨刚. 自适应前馈神经网络结构优化设计[J]. 智能系统学报, 2011, 6(4): 312-316.
[2]  (Zhang Z Z, Qiao J F, Yang G. An adaptive algorithm for designing optimal feed-forward neural network architecture[J]. CAAI Trans on Intelligent Systems, 2011, 6(4): 312-316.)
[3]  李倩, 王永县, 朱友芹. 人工神经网络混合剪枝算法[J]. 清华大学学报: 自然科学版, 2005, 45(6):831-834.
[4]  (Li Q, Wang Y X, Zhu Y Q. Hybrid pruning algorithm for artificial neural network training[J]. J of Tsinghua University: Science and Technology, 2005, 45(6): 831-834.)
[5]  Philippe Lauret, Eric Fock, Thierry Alex Mara. A node pruning algorithm based on a fourier amplitude sensitivity test method[J]. IEEE Trans on Neural Networks, 2006,17(2): 273-293.
[6]  Monirul Islam, Abdus Sattar, Faijul Amin, et al. A new adaptive merging and growing algorithm for designing artificial neural networks[J]. IEEE Trans on Systems, Man and Cybernetics—Part B: Cybernetics, 2009, 39(3): 705-722.
[7]  韩红桂, 李淼, 乔俊飞. 基于模型输出敏感度分析的动态神经网络结构设计[J]. 电子学报, 2010, 38(3): 731-736.
[8]  (Han H G, Li M, Qiao J F. Design of dynamic neural network based on the sensitivity analysis of model output[J]. Acta Electronica Sinica, 2010, 38(3): 731-736.)
[9]  张昭昭, 乔俊飞, 韩红桂. 一种基于神经网络复杂度的修剪算法[J]. 控制与决策, 2010, 25(6): 821-830.
[10]  (Zhang Z Z, Qiao J F, Han H G. A pruning algorithm based on neural complexity[J]. Control and Decision, 2010, 25(6): 821-830.)
[11]  魏海坤. 神经网络结构设计的理论与方法[M]. 北京: 国防工业出版社, 2005: 228-233.
[12]  (Wei H K. The theory and method of neural network structure design[M]. Beijing: National Defense Industry Press, 2005: 228-233.)
[13]  Weigend A S, Rumelhart D E, Huberman B A. Generalization by weight-elimination applied to currency exchange rate prediction[C]. Proc of the Int Joint Conf on Neural Networks. Seattle, 1991: 837-841.
[14]  Liu H, Setiono R. Feature selection via discretization[J]. IEEE Trans on Knowledge and Data Engineering, 1997, 9(4): 642-645.
[15]  Wong S K M, Ziarko W. On optimal decision rules in decision tables[J]. Bulletin of the Polish Academy of Sciences, 1985, 33(11/12): 693-696.
[16]  吴静, 邹海. 基于属性重要性的属性约简算法[J]. 计算机应用与软件, 2010, 27(2): 255-257.
[17]  (Wu J, Zou H. Attribute reduction algorithm based on importance of attribute value[J]. Computer Applications and Software, 2010, 27(2): 255-257.)
[18]  任小康, 吴尚智, 马如云. 基于可辨识矩阵的属性频率约简算法[J]. 兰州大学学报, 2007, 43(1): 138-140.
[19]  (Ren X K, Wu S Z, Ma R Y. Attribute reduction algorithm based on discernibility matrix[J]. J of Lanzhou University, 2007, 43(1): 138-140.)
[20]  Meng Yue-bo, Zou Jian-hua, Gan Xu-sheng, et al. Research on WNN aerodynamic modeling from flight data based on improved PSO algorithm[J]. Neurocomputing, 2012, 83(4): 212-221.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133