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...
电子学报  2014 

混合逆狄利克雷分布的变分学习及应用

DOI: 10.3969/j.issn.0372-2112.2014.07.030, PP. 1435-1440

Keywords: 逆狄利克雷分布,贝叶斯估计,变分推理,拓展分解变分近似,模型选择

Full-Text   Cite this paper   Add to My Lib

Abstract:

混合逆狄利克雷分布是正的非高斯数据分析中一个重要的统计模型.但是利用常用的统计方法比如极大近似然估计、矩估计等往往很难得到模型参数估计的显性解析式.本文提出一个变分贝叶斯学习算法,它能够在估计参数的同时自动确定混合分量数.在合成数据集及实测数据集上的实验结果表明利用变分贝叶斯推理来估计混合逆狄利克雷分布是一种非常有效的方法.

References

[1]  左国玉,刘文举,阮晓钢.声音转换技术的研究与进展 [J].电子学报,2002,32(7):1165-1172. Zuo G Y,Liu W J,Ruan X G.A voice conversion te-chnology and development [J].Acta Electronica Sinia,2002,30(10):1438-1440.(in Chinese)
[2]  梁岩,鲍长春,夏丙寅,等.基于高斯混合模型的压缩域语音增强方法[J].电子学报,2012,40(10):2031-2038. Liang Y,Bao C C,Xia BY,et al.Compressed domain speech enhancement based on Gaussian mixture model [J].Acta Electronica Sinica,2012,40(10):2031-2038.(in Chinese)
[3]  刘立芳,霍红卫,王宝树.生物序列模体的混合Gibbs 抽样识别算法[J].电子学报,2008,36(4):750-755. Liu L F,Huo H W,Wang B S.Multiple motif discovery in biological sequences by mixture Gibbs sampling [J].Acta Electronica Sinica,2008,36(4):750-755.(in Chinese)
[4]  Bdiri T,Bouguila N.Positive vectors clustering using interted Dirichlet finite mixture Models [J].Expert Systems with Applications,2012,39(2):1869-1882.
[5]  Bouguila N,ElGuebaly W.Discrete data clustering using finite mixture models[J].Pattern Recognition,2009,42(1):33-42.
[6]  Ma Z Y,Leijon A.Bayesian estimation of beta mixture models with variational inference [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(33):2160-2173.
[7]  Fan W T,Bouguila,Ziou N.Variaional learning for finite Dirichlet mixture models and applications [J].IEEE Transaction on Neural Networks and Learning Systems,2012,23(5):762-774.
[8]  Bouguila N.Hybrid Generative/discriminative approaches for proportional data modeling and classification[J].IEEE Transactions on Knowledge and Data Engineering,2012,24(12):2184-2202.
[9]  刘伟峰,杨爱兰.基于BIC 准则和Gibbs 采样的有限混合模型无监督学习算法[J].电子学报,2011,39(3A):134-139. Liu W F,Yang A L.Unsupervised learning for finite mixture models based on BIC criterion and gibbs sampling[J].Acta Electronica Sinica,2011,39(3A):134-1139.(in Chinese)
[10]  Corduneanu A,Bishop C.Variational Bayesian model selection for mixture distributions[A].Proceeding of the 8th International Conference on Artificial Intelligece and Statistics[C].USA:IEEE,2001.27-34.
[11]  Bishop C M.Pattern Recognition and Machine Learning [M].New York:Springer-Verlag,2006.
[12]  Wang B,Titterington D M.Convergence and asymptotic normality of variational Bayesian approxima-tions for exponential family models with missing values[A].Proc.UAI[C]USA:IEEE,2004.577-584.
[13]  David MBlei,Andrew Y Ng,Michael I jordan.latent dirichlet allocation[J].Journal of Machine Learning Research,2003,3(33):993-1022.
[14]  JosefSivic,Andrew Zisserman.Video google:A text retrieval approach to object matching in videos [A].Proceedings of Ninth IEEE International Conference on Computer Vision[C].USA:IEEE,2003,1470-1477.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133