Proceedings of the KAIS Fall Conference (한국산학기술학회:학술대회논문집)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지

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

신경망과 유전 알고리즘을 사용한 비선형 시스템의 최적 제어

  • Cho Hyeon-Seob (Dep. of Electronics Engineering Chungwoon University Graduate School) ;
  • Min Jin-Kyoung (Dep. of Electronics Engineering Chungwoon University Graduate School) ;
  • Lee Hyung-Chung (Dep. of Electronics Engineering Kyung-hee University Techbo Management Graduate School)
  • 조현섭 (청운대학교 대학원) ;
  • 민진경 (청운대학교 대학원) ;
  • 이형충 (경희대학교 테크노 경영대학원)
  • Published : 2004.06.01
Download PDF
⟨ Previous Next ⟩

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 loaming 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