Neural Network Design for Spatio-temporal Pattern Recognition

시공간패턴인식 신경회로망의 설계

  • Published : 1999.11.01

Abstract

This paper introduces complex-valued competitive learning neural network for spatio-temporal pattern recognition. There have been quite a few neural networks for spatio-temporal pattern recognition. Among them, recurrent neural network, TDNN, and avalanche model are acknowledged as standard neural network paradigms for spatio-temporal pattern recognition. Recurrent neural network has complicated learning rules and does not guarantee convergence to global minima. TDNN requires too many neurons, and can not be regarded to deal with spatio-temporal pattern basically. Grossberg's avalanche model is not able to distinguish long patterns, and has to be indicated which layer is to be used in learning. In order to remedy drawbacks of the above networks, unsupervised competitive learning using complex umber is proposed. Suggested neural network also features simultaneous recognition, time-shift invariant recognition, stable categorizing, and learning rate modulation. The network is evaluated by computer simulation with randomly generated patterns.

Keywords

References

  1. Neural networks Algorithms, Application, and Programming techinques James A.Freeman;David M.Skapura
  2. Proceedings on ICNN v.13 A Hybrid Neural Network for Spatio-temporal Pattern Recognition Yifeng Chen;Yuanda Cao
  3. Neural Networks for Pattern Recognition Albert Nigrin
  4. Neurocomputing no.15 Habituatin Based Neural Networks for Spatio-temporal Classification Bryan W.Stiles;Joydeep Ghosh
  5. 인공지능, 신경회로망 및 퍼지 관련 학술대회 논문집 시공간 패턴 인식기를 이용한 숫자음 인식 김헌기;박경철;이종호