• DocumentCode
    2292724
  • Title

    Partitioned mixture distributions: a first order perturbation analysis

  • Author

    Luttrell, S.P.

  • Author_Institution
    Defence Res. Agency, Malvern, UK
  • fYear
    1997
  • fDate
    7-9 Jul 1997
  • Firstpage
    280
  • Lastpage
    284
  • Abstract
    A perturbation analysis is used to linearise the theory of partitioned mixture distribution (PMD) encoder/decoder networks, which allows many connections to be made with previous results. For instance, the difference of Gaussians (DOG) filtering operation commonly used in image processing emerges very naturally, and the dependence of the wavelength of dominance stripes in a visual cortex network (VICON) may then be derived
  • Keywords
    image processing; decoder networks; difference of Gaussians filtering operation; dominance stripes; encoder networks; first order perturbation analysis; image processing; partitioned mixture distributions; visual cortex network;
  • fLanguage
    English
  • Publisher
    iet
  • Conference_Titel
    Artificial Neural Networks, Fifth International Conference on (Conf. Publ. No. 440)
  • Conference_Location
    Cambridge
  • ISSN
    0537-9989
  • Print_ISBN
    0-85296-690-3
  • Type

    conf

  • DOI
    10.1049/cp:19970740
  • Filename
    607531