多層競合ネットによる座標変換に不変なパターン認識  [in Japanese] A Multi-Layered Competitive Net for Pattern Recognition Invariant to Coordinate Transformations  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

A multi-layered competitive neural network is presented for learning to achieve pattern recognition in a manner invariant to linear and/or nonlinear coordinate transformations such as projection, shift, rotation, magnification and so on. The transformed input patterns stored in the network are multiplied by the Jacobian of the transformation, an aspect shown to be essential for the transformation invariance. The network also has excellent generalization ability as has been verified by computer simulation.

Journal

  • The Brain & Neural Networks

    The Brain & Neural Networks 7(4), 106-114, 2000-12-05

    Japanese Neural Network Society

References:  13

Codes

  • NII Article ID (NAID)
    10008841723
  • NII NACSIS-CAT ID (NCID)
    AA11658570
  • Text Lang
    JPN
  • Article Type
    ART
  • ISSN
    1340766X
  • Data Source
    CJP  J-STAGE 
Page Top