Dynamic Neural Units and Genetic Algorithms With Applications to the Control of Unknown Nonlinear Systems

동적 신경망과 Geneo-tic Algorithms를 적용한 비선형 시스템의 제어

  • Cho, Hyun-Seob (Dept of Digital Broadcast Engineering Chungwoon University) ;
  • Min, Jin-Kyoung (Dept of Digital Broadcast Engineering Chungwoon University) ;
  • Roh, Yong-Gi (Dept of Electrical Engineering Wonkwang University) ;
  • Jung, Byung-Jo (Dept of Electrical Engineering Wonkwang University) ;
  • Jang, Sung-Whan (Dept of Electrical Engineering Wonkwang University)
  • 조현섭 (청운대학교 디지털방송공학과) ;
  • 민진경 (청운대학교 디지털방송공학과) ;
  • 노용기 (원광대학교 전기공학과) ;
  • 정병조 (원광대학교 전기공학과) ;
  • 장성환 (원광대학교 전기공학과)
  • Published : 2006.07.12

Abstract

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin

Keywords