期刊文献+

距离加权的2-D核自联想记忆模型及其应用 被引量:2

Distance Weighted 2-D Kernel Auto-Association Memory Model and Its Applications
原文传递
导出
摘要 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(IEC-AM)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. By using the kernel trick to modify Hopfield auto-associative memory model (HAM), a framework of kernel auto-association memory model (KAM) is proposed. KAM makes exponential correlation associative memory ( ECAM ) and improved ECAM ( IECAM ) become two special cases. Then, the framework of distance weighted 2-D kernel auto-association memory model (DW2D-KAM) is constructed by introducing distance factors tO the kernels. DW2D-KAM improves the Storage capacity and error-correcting capability of KAM when recognizing binary visual images. Simulation results verify that DW2D-KAM has higher storage capacity and better error-correcting capability than those of KAM, and outperforms the recently proposed modular HAM by Seow and Asari.
出处 《模式识别与人工智能》 EI CSCD 北大核心 2007年第1期110-114,共5页 Pattern Recognition and Artificial Intelligence
基金 国家自然科学基金(No.60271017)
关键词 自联想记忆 神经网络 距离加权 核方法 模式识别 Auto-Association Memory, Neural Network, Distance Weighted, Kernel Method,Pattern Recognition
  • 相关文献

参考文献15

  • 1Hopfield J J. Neural Network and Physical Systems with Emergent Collective Computational Abilities. Proc of the National Academy of Sciences of the United States of America, 1982, 79(8) : 2554-2558 被引量:1
  • 2周志华,曹存根主编..神经网络及其应用[M].北京:清华大学出版社,2004:445.
  • 3Psaltis 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 被引量:1
  • 4Dembo A, Zeitouni O. General Potential Surfaces and Neural Networks. Physics Review A: General Physics, 1988, 37 (6) :2134-2143 被引量:1
  • 5Chiueh T D, Goodman R M. Recurrent Correlation Associative Memories. IEEE Trans on Neural Networks, 1991, 2(2) :275-284 被引量:1
  • 6Zhang 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 被引量:1
  • 7Nowicki D, Dekhtyarenko 0. Kernel-Based Associative Memory// Proc of the IEEE International Joint Conference on Neural Networks. Budapest, Hungary, 2004, I. 741-744 被引量:1
  • 8Garcia 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 被引量:1
  • 9Caputo B, Niemann H. Storage Capacity of Kernel Associative Memories // Proc of the International Conference on Artificial Neural Network. Madrid, Spain, 2002:51-56 被引量:1
  • 10Mercer 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 被引量:1

同被引文献29

  • 1芮挺,沈春林,张金林.基于字符特征的车牌英文和数字字符自联想识别[J].模式识别与人工智能,2004,17(4):467-472. 被引量:3
  • 2陈蕾,陈松灿,张道强.小世界体系的多对多核联想记忆模型及其应用[J].软件学报,2006,17(2):223-231. 被引量:9
  • 3许跃,朱伟兴.基于自联想神经网络的传感器故障诊断[J].传感器与微系统,2007,26(4):94-96. 被引量:2
  • 4Hopfield J J. Neural network and physical systems with emergent collective computational abilities[J]. Nat. Aead. Sci., 1982 (79) : 2554 - 2558. 被引量:1
  • 5Hopfield J J. Neurons with grade response have collective computational properties like those of two- state neurons [C]// Proceedings of the National Academy of Sciences. USA: 1984(81) : 3088 - 3092. 被引量:1
  • 6Chen Z Y, Kwong C P. Recurrent correlation associative memories with multiplevalue[J]. IEEE Int. CoM. Neural Networks, 1994,2(2) : 1068 - 1073. 被引量:1
  • 7Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE Trans. on Neural Networks, 1995,10(5) : 1055 - 1064. 被引量:1
  • 8Seow M J, Asari V K. Learning using distance based training algorithm for pattern recognition[J]. Pattern Recognition Letters, 2004, 25(2) : 189- 196. 被引量:1
  • 9Phillips P J, Weehsler H, Huang J, et al. The FERET database and evaluation procedure for face recognition algorithms[J]. Image and Vision Computing, 1998, 16(5): 295 - 306. 被引量:1
  • 10周志华,曹存根.神经网络的研究和进展[M].北京:清华大学出版社,2004. 被引量:1

引证文献2

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部