대한전기학회:학술대회논문집 (Proceedings of the KIEE Conference)

대한전기학회 (The Korean Institute of Electrical Engineers)
권호 표지

시변패턴 인식을 위한 2단 구조의 신경회로망

Two stage neural network for spatio-temporal pattern recognition

  • 임정수 (인하대학교 전기공학과) ;
  • 이종호 (인하대학교 전기공학과)
  • Lim, Chung-Soo (Department of Electrical Engineering, Inha University) ;
  • Lee, Chong-Ho (Department of Electrical Engineering, Inha University)
  • 발행 : 1998.07.20
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper introduces Two-stage neural network that is capable of recognizing spatio-temporal patterns. First stage takes a spatio-temporal pattern as input and compress it into sparse spatio-temporal pattern. Second stage is for temporal pattern recognition with nonuniform inhibitory connections and different cell sizes. These are basic properties for detecting a embeded pattern in a larger pattern. The network is evaluated by computer simulation.

키워드