期刊文献+

Counterexamples to convergence theorem of maximum-entropy clustering algorithm 被引量:6

Counterexamples to convergence theorem of maximum-entropy clustering algorithm
原文传递
导出
摘要 In this paper, we surveyed the development of maximum-entropy clustering algorithm, pointed out that the maximum-entropy clustering algorithm is not new in essence, and constructed two examples to show that the iterative sequence given by the maximum-entropy clustering algorithm may not converge to a local minimum of its objective function, but a saddle point. Based on these results, our paper shows that the convergence theorem of maximum-entropy clustering algorithm put forward by Kenneth Rose et al. does not hold in general cases. In this paper, we surveyed the development of maximum-entropy clustering algorithm, pointed out that the maximum-entropy clustering algorithm is not new in essence, and constructed two examples to show that the iterative sequence given by the maximum-entropy clustering algorithm may not converge to a local minimum of its objective function, but a saddle point. Based on these results, our paper shows that the convergence theorem of maximum-entropy clustering algorithm put forward by Kenneth Rose et al. does not hold in general cases.
出处 《Science in China(Series F)》 2003年第5期321-326,共6页 中国科学(F辑英文版)
关键词 ENTROPY fixed point clustering algorithm convergence. entropy, fixed point, clustering algorithm, convergence.
  • 相关文献

参考文献9

  • 1[1]Rose, K., Gurewtiz, E., Fox, G., A deterministic annealing approach to clustering, Pattern Recognition Letters, 1990, 11: 589-594.
  • 2[2]Karayiannis, N. B., MECA: Maximum entropy clustering algorithm, in Proc. IEEE Int. Conf. Fuzzy Syst., Orlando, FL, June 26-29, 1994, 630-635.
  • 3[3]Li, R._P., Mukaidono, M., A maximum entropy approach to fuzzy clustering, Proc. of the 4th IEEE Intern. Conf. on Fuzzy Systems, Yokohama, Japan, March 20-24, 1995, 2227-2232.
  • 4[4]Karayiannis, N. B., Fuzzy partition entropies and entropy constrained fuzzy clustering algorithms, J. Intell. Fuzzy Syst., 1997, 5(2): 103-111.
  • 5[5]Miyamoto, S., Mukaidono, M., Fuzzy c-means as a regularization and maximum entropy approach, Proc. of the 7th International Fuzzy Systems Association World Congress, Vol. II, June 25-30, Prague, Chech, 1997, 86-92.
  • 6[6]Karayiannis, N. B., An axiomatic approach to soft learning vector quantization and clustering, IEEE Trans. on Neural Networks, 1999, 10(5): 1153-1165.
  • 7[7]Miyamoto, S., Umayahara, K., Two methods of fuzzy c-means and classification functions, Proc. of 6th Conf. of the International Federation of Classification Societies, July 21-24, Roma, Italy, 1998, 105-110.
  • 8[8]Zhang Zhihua, Zheng Nanning, Shi Gang, Maximum-entropy clustering algorithm and its global convergence analysis, Science in China, Ser. E, 2001, 44(1): 89-101.
  • 9[9]Rose, K., Deterministic annealing for clustering, compression, classification, regression, and related optimization problems, Proceedings of the IEEE, 1998, 86(11): 2210-2239.

同被引文献30

  • 1张志华,郑南宁,史罡.Maximum-entropy clustering algorithm and its global convergence analysis[J].Science China(Technological Sciences),2001,44(1):89-101. 被引量:3
  • 2张敏,于剑.基于划分的模糊聚类算法[J].软件学报,2004,15(6):858-868. 被引量:179
  • 3彭宁嵩,杨杰,刘志,张风超.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9):1542-1550. 被引量:165
  • 4Rose K,Gurewtiz E,Fox G.A deterministic annealing approach to clustering. Pattern Recognition . 1990
  • 5Karayiannis N B.An axiomatic approach to soft learn ingvector quantization and clustering. IEEE ACM Transactions on Networking . 1999
  • 6Karayiannis N,B Meca.Maximum entropy clustering algorithm. Proc IEEE Conf Fuzzy Syst . 1994
  • 7Li R P,Mukaidon M.A maximum entropy approach to fuzzy clustering. Proceedings of the 4th IEEE International Conference onFuzzy System . 1995
  • 8Karayiannis N B.Fuzzy partition entropies and entropy constrained fuzzy clustering algorithms. J Intell Fuzzy Syst . 1997
  • 9Miyamoto S,Mukaidono M.Fuzzy c-means as aregularization and maximum entropy approach. Proceedings of the 7th International Fuzzy SystemsAssociation World Congress (IFSA’97), Prague: Chech . 1997
  • 10Miyamoto S,,Umayahara K.Two methods of fuzzy c-meansand classification functions. Proceedings of the 6thConference of the International Federation of ClassificationSocieties . 1998

引证文献6

二级引证文献233

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