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...

距离加权的2D核自联想记忆模型及其应用*

, PP. 110-114

Keywords: 自联想记忆,神经网络,距离加权,核方法,模式识别

Full-Text   Cite this paper   Add to My Lib

Abstract:

首先从Hopfield自联想记忆模型(HAM)出发,对其回忆规则运用机器学习中流行的核技巧,构建一个核自联想记忆模型框架(KAM).并通过核函数的选取,使指数型相关联想记忆模型(ECAM)和改进的ECAM(IECAM)模型成为其中的两个特例.然后针对二维视觉图像的识别,在核函数中引入反映视觉特性的二维(2D)距离因子,进一步提出一个距离加权的2D核自联想记忆模型框架(DW2DKAM).由此较大改进KAM对图像的存储和纠错性能,并且使该模型更加符合神经生理学和解剖学的思想.最后,计算机模拟不仅证实DW2DKAM比KAM在字符识别上具有更高的存储和纠错性能,而且其同样优于Seow和Asari提出的模块化HAM的识别效果.

References

[1]  Hopfield J J. Neural Network and Physical Systems with Emer gent Collective Computational Abilities. Proc of the National Academy of Sciences of the United States of America, 1982, 79(8): 25542558
[2]  Psaltis D, Park H C. Nonlinear Discriminant Functions and Associative Memories // Proc of the AIP Conference on Neural Networks for Computing. Snowbird, USA, 1987: 370375
[3]  García C, Moreno J A, Sloot P M A, et al. The Kernel Hopfield Memory Network // Proc of the 6th International Conference on Cellular Automata for Research and Industry. Amsterdam, Netherlands, 2004: 755764
[4]  Caputo B, Niemann H. Storage Capacity of Kernel Associative Memories // Proc of the International Conference on Artificial Neural Network. Madrid, Spain, 2002: 5156
[5]  Mercer J. Functions of Positive and Negative Type, and Their Connection with the Theory of Integral Equations. Philosophical Transaction of the Royal Society of London, 1909, 209: 415466
[6]  Cristianini N, ShaweTaylor J. An Introduction to Support Vector Machines and Other KernelBased Learning Methods. Cambridge, UK: Cambridge University Press, 2000
[7]  Gazzaniga M S. Organization of the Human Brain. Science, 1989, 245(492): 947952
[8]  Kohonen T. SelfOrganizing Maps. 2nd Edition. Berlin, Germany: SpringerVerlag, 1997
[9]  Seow M J, Asari V K. Learning Using Distance Based Training Algorithm for Pattern Recognition. Pattern Recognition Letters, 2004, 25(2): 189196
[10]  Boser B E, Guyon I M, Vapnik V N. A Training Algorithm for Optimal Margin Classifiers // Proc of the 5th Annual Workshop on Computational Learning Theory. San Mateo, USA, 1992: 144152
[11]  Zhou Zhihua, Cao Cungen. Neural Network and Applications. Beijing, China: Tsinghua University Press, 2004: 295320 (in Chinese) (周志华,曹存根.神经网络及其应用.北京:清华大学出版社, 2004: 295320)
[12]  Dembo A, Zeitouni O. General Potential Surfaces and Neural Networks. Physics Review A: General Physics, 1988, 37 (6): 21342143
[13]  Chiueh T D, Goodman R M. Recurrent Correlation Associative Memories. IEEE Trans on Neural Networks, 1991, 2(2): 275284
[14]  Zhang Bailing, Zhang Haihong, Ge S Z S. Face Recognition by Applying Wavelet Subband Representation and Kernel Associative Memory. IEEE Trans on Neural Networks, 2004, 15(1): 166177
[15]  Nowicki D, Dekhtyarenko O. KernelBased Associative Memory // Proc of the IEEE International Joint Conference on Neural Networks. Budapest, Hungary, 2004, Ⅰ: 741744

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133