다중 역전파 신경회로망을 이용한 비선형 시스템의 모델링

• 영문명: Nonlinear System Modeling Based on Multi-Backpropagation Neural Network
• 발행기관: 강원대학교 산업기술연구소
• 저자명: 백재혁(Jae Huyk Baeg) 이정문(Jung Moon Lee)
• 간행물 정보: 『산업기술연구』vol.16, 197~205쪽, 전체 9쪽
• 주제분류: 공학 > 공학일반
• 파일형태: PDF
• 발행일자: 1996.09.30

영문 초록

In this paper, we propose a new neural architecture. We synthesize the architecture from a combination of structures known as MRCCN (Multi-resolution Radial-basis Competitive and Cooperative Network) and BPN (Backpropagation Network). The proposed neural network is able to improve the learning speed of MRCCN and the mapping capability of BPN. The ability and effectiveness of identifying a ninlinear dynamic system using the proposed architecture will be demonstrated by computer simulation.

목차

ABSTRACT

1. 서론

2. 비선형 시스템의 표현

3. 신경희로망의 소개

4. 모의실험

5. 결론

참고문헌