• DocumentCode
    1942424
  • Title

    Orientation Selectivity of TAM Network with Extensive Receptive Field

  • Author

    Hayashi, Isao ; Williamson, James R.

  • Author_Institution
    Dept. of Informatics, Kansai Univ., Osaka
  • Volume
    1
  • fYear
    2005
  • fDate
    28-30 Nov. 2005
  • Firstpage
    1184
  • Lastpage
    1189
  • Abstract
    TAM (topographic attentive mapping) network is a biologically-motivated neural network with Gabor function type receptive fields. However, the structure of receptive fields is a mono-layer, and there is a lack of performance for rotating images. In this paper, we formulate a new TAM network with multilayer structure of extensive receptive fields. We also show the usefulness of TAM network using some examples of character recognition
  • Keywords
    Gabor filters; character recognition; neural nets; Gabor function; TAM network; biologically-motivated neural network; character recognition; image rotation; multilayer structure; receptive field; topographic attentive mapping network; Character recognition; Filtering; Gabor filters; Humans; Informatics; Multi-layer neural network; Neural networks; Object detection; Retina; Visual system;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on
  • Conference_Location
    Vienna
  • Print_ISBN
    0-7695-2504-0
  • Type

    conf

  • DOI
    10.1109/CIMCA.2005.1631423
  • Filename
    1631423