The independence assumption:: Analyzing the independence of the components by topography

被引:0
|
作者
Hyvärinen, A [1 ]
Hoyer, PO [1 ]
Inki, M [1 ]
机构
[1] Helsinki Univ Technol, Neural Networks Res Ctr, FIN-02015 Helsinki, Finland
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In ordinary independent component analysis, the components are assumed to be completely independent, and they do not necessarily have any meaningful order relationships. In practice, however, the estimated "independent" components are often not at all independent. We propose that this residual dependence structure could be used to define a topographic order for the components. In particular, a distance between two components could be defined using their higher-order correlations, and this distance could be used to create a topographic representation. Thus we obtain a linear decomposition into approximately independent components, where the dependence of two components is approximated by the proximity of the components in the topographic representation.
引用
收藏
页码:45 / 62
页数:18
相关论文
共 50 条
  • [31] Pairwise multiple comparisons under violation of the independence assumption
    Seco, GV
    de la Fuente, IAM
    Escudero, JR
    QUALITY & QUANTITY, 2001, 35 (01) : 61 - 76
  • [32] Independence assumption: a dispensable tool in adaptive filter theory
    Eindhoven Univ of Technology, Eindhoven, Netherlands
    Signal Process, 3 (305-310):
  • [33] Multimode independent component analysis and relaxing independence assumption
    Miyamoto, Yusuke
    INTERNATIONAL JOURNAL OF PSYCHOLOGY, 2008, 43 (3-4) : 111 - 111
  • [34] Selectivity estimation without the attribute value independence assumption
    Poosala, V
    Ioannidis, YE
    PROCEEDINGS OF THE TWENTY-THIRD INTERNATIONAL CONFERENCE ON VERY LARGE DATABASES, 1997, : 486 - 495
  • [35] TESTING THE ASSUMPTION OF INDEPENDENCE OF TRUNCATION TIME AND FAILURE TIME
    TSAI, WY
    BIOMETRIKA, 1990, 77 (01) : 169 - 177
  • [36] A TEST OF THE CONDITIONAL INDEPENDENCE ASSUMPTION IN SAMPLE SELECTION MODELS
    Huber, Martin
    Melly, Blaise
    JOURNAL OF APPLIED ECONOMETRICS, 2015, 30 (07) : 1144 - 1168
  • [37] Recent Advances in Overcoming the Independence Assumption in Adaptive Filtering Analyses
    Silva, Thiago T. P.
    Lara, Pedro
    Gonzaga, Thiago
    Brandao, Diego
    Tarrataca, Luis
    Haddad, Diego B.
    PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING (IWSSIP), 27TH EDITION, 2020, : 317 - 322
  • [38] Generalized instrumental inequalities: testing the instrumental variable independence assumption
    Kedagni, Desire
    Mourifie, Ismael
    BIOMETRIKA, 2020, 107 (03) : 661 - 675
  • [39] On testing the strength independence assumption in retrieval-induced forgetting
    Raaijmakers, Jeroen G. W.
    PSYCHONOMIC BULLETIN & REVIEW, 2016, 23 (05) : 1374 - 1381
  • [40] How conditional independence assumption affects handwritten character segmentation
    Maragoudakis, M
    Kavallieratou, E
    Fakotakis, N
    Kokkinakis, G
    SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 246 - 250