期刊文献+

混合高斯模型的熵惩罚最大似然估计与自动模型选择

Entropy Penalized Maximum-Likelihood Estimate on Gaussian Mixture with Automated Model Selection
下载PDF
导出
摘要 有限高斯混合模型是一种重要的概率模型,并在聚类分析,模式识别和信号处理等方面有着广泛的应用.在高斯(即正态)分量个数K未知时,仅仅根据样本数据来确定K是一个非常困难的问题.这实际上是一个模型选择问题,直接影响着应用的效果.为了解决这一模型选择问题,本文在一维混合高斯模型下提出了基于熵惩罚最大似然估计的梯度算法.实验表明这种算法能够在参数估计过程中自动实现模型选择,使得多余高斯分量的混合比例系数衰减为零.
出处 《信号处理》 CSCD 2003年第z1期253-256,共4页 Journal of Signal Processing
基金 本项目受国家自然科学基金资助:60071004
  • 相关文献

参考文献11

  • 1[1]G. J. Mclachlan and K. E. Basford, Mixture Models: Inference and Applications to Clustering, New York: Marcel Dekker, 988.
  • 2[2]R. A. Render and H. F. Walker,"Mixture densities,maximum likelihood and the EM algorithm",SIAM Review, vol.26, no.2, pp. 195-239, 1984.
  • 3[3]J. A. Hartigan, "Distribution problems in clustering," Classification and clustering, J.Van Ryzin Eds., pp. 45-72, New York:Academic Press, 1977.
  • 4[4]H. Akaike, "A New Look at the Statistical Model Identification", IEEE Transac-ons on Automatic Control, vol. AC-19, pp. 716-723,1974.
  • 5[5]H. Bozdogan, Multiple Sample Cluster Analysis and Approachesto Validity Studies in Clustering Individuals, Doctoral Dissertation,University of Illinois at Chicago Circle, 1981.
  • 6[6]H. Bozdogan, "Model Selection and Akaike′s Information Criterion: The General Theory and its Analytical Extensions", Psychometrika,vol.52, no.3, pp. 345-370, 1987.
  • 7[7]G. Scharz, "Estimating the dimension of a model",The Annals of Statistics, vol.6, no.2, pp.461-464, 1978.
  • 8[8]Jinwen Ma, Taijun Wang and Lei Xu, "An adaptive BYY harmony learning algorithm and its relation to rewarding and penalizing learning mechanism", Proc. of ICSP′02, vol.2,pp:1154-1158.
  • 9[9]Jinwen Ma, Taijun Wang and Lei Xu, "An iterative algorithm for BYY Learning on Gaussian mixture with automated model selection", To appear in Proc. of ICNNSP′03.
  • 10[10]Jinwen Ma, Taijun Wang and Lei Xu, "Two annealing Algorithms for BYY learning on Gaussian mixture with automated model selection", To appear in Proc. of ICNNSP′03.

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