지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2011.8
- 수록면
- 777 - 782 (6page)
이용수
초록· 키워드
오류제보하기
Neural network technique is widely employed in the fields of signal processing, control systems, pattern recognition, etc. Learning of neural networks is an important procedure to accomplish dynamic system modeling. This paper presents a novel learning approach for differential neural network models based on the Kalman-Bucy filter theory. We construct an augmented state vector including original neural state and parameter vectors and derive a state estimation rule avoiding gradient function terms which involve to the conventional neural learning methods such as a back-propagation approach. We carry out numerical simulation to evaluate the proposed learning approach in nonlinear system modeling. By comparing to the well-known back-propagation approach and Kalman-Bucy filtering, its superiority is additionally proved under stochastic system environments.
목차
Abstract
Ⅰ. 서론
Ⅱ. 칼만-버쉬 필터 알고리즘
Ⅲ. 미분 신경회로망
Ⅳ. 칼만-버쉬 필터링 기반 미분 신경회로망 학습
Ⅴ. 컴퓨터 시뮬레이션
Ⅵ. 결론
참고문헌
참고문헌 (17)
참고문헌 신청
1. [학술대회논문] - S. Li / 2001 / Comparative analysis of backpropagation and extended Kalman filter in pattern and batch forms for training neural networks / International Joint Conference on Neural Networks : 144 ~ 149
2. [학술대회논문] - C. M. Takenga / 2004 / Comparison of gradient descent method, Kalman filtering and decoupled Kalman in training neural networks used for fingerprint-based positioning / Proc. of the IEEE Vehicular Technology Conference : 4146 ~ 4150
3. [학술지(정기간행물)] - K.-W. Wong / 2002 / Use pf periodic and monotonic activation functions in multilayer feedforward neural networks trained by extended Kalman filter algorithm / IEEE Image Signal Process 149 (4) : 217 ~ 224
4. [학술지(정기간행물)] - S. J. Julier / 2004 / Unscented filtering and nonlinear estimation / Proc. of the IEEE 92 (3) : 401 ~ 422
5. [학술대회논문] - B. Todorovic / 2003 / On-line learning in recurrent neural networks using nonlinear Kalman filters / Proc. of the IEEE Int. Symposium on Signal Processing and Information Technology : 802 ~ 805
2. [학술대회논문] - C. M. Takenga / 2004 / Comparison of gradient descent method, Kalman filtering and decoupled Kalman in training neural networks used for fingerprint-based positioning / Proc. of the IEEE Vehicular Technology Conference : 4146 ~ 4150
3. [학술지(정기간행물)] - K.-W. Wong / 2002 / Use pf periodic and monotonic activation functions in multilayer feedforward neural networks trained by extended Kalman filter algorithm / IEEE Image Signal Process 149 (4) : 217 ~ 224
4. [학술지(정기간행물)] - S. J. Julier / 2004 / Unscented filtering and nonlinear estimation / Proc. of the IEEE 92 (3) : 401 ~ 422
5. [학술대회논문] - B. Todorovic / 2003 / On-line learning in recurrent neural networks using nonlinear Kalman filters / Proc. of the IEEE Int. Symposium on Signal Processing and Information Technology : 802 ~ 805
이 논문의 저자 정보
이 논문과 함께 이용한 논문
모바일 로봇 자세 안정화를 위한 칼만 필터 기반 센서 퓨전
장태호
,
김영식
,
경민영
외 2명
대한기계학회 논문집 A권
2016
.08
A-Si(CsITl) 영상시스템에서 부가필터, SID에 따른 X선 스펙트럼변화와 해상력에 대한 고찰
안현
,
김정훈
,
이동연
외 2명
한국콘텐츠학회논문지
2016
.07
지자기맵을 이용한 이동로봇의 실내 위치 추정
김태경
,
국태용
,
박종구
외 1명
대한전자공학회 학술대회
2016
.06
Hysteresis Modeling of the Sealed Flooded Lead Acid Battery for SOC Estimation
Abdul Basit Khan
,
Woojin Choi
전력전자학회 학술대회 논문집
2016
.07
The Study of Particle Filter Localization Algorithm Based on Magnetic Field Data
Chang
,
Kun
,
Huang
외 5명
대한공간정보학회지
2016
.06
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2013-569-003260936