摘要
This paper addresses the problem that network whose parameters are updated using EKF can not obtain robust performance if the system state saltates when EKF reach stable state. Strong tracking filter which introduces suboptimal fading factor matrix to overcome the problem is utilized to adjust the network parameters to obtain robust performance. The winner neuron updating strategy is also employed to reduce the computation load for online application. Experimental results show the proposed algorithm can achieve smaller approximation error and more compact network structure than several other typical sequential learning algorithms.
源语言 | 英语 |
---|---|
主期刊名 | 8th International Conference on Signal Processing, ICSP 2006 |
出版商 | Institute of Electrical and Electronics Engineers Inc. |
ISBN(印刷版) | 0780397371, 9780780397378 |
DOI | |
出版状态 | 已出版 - 2006 |
活动 | 8th International Conference on Signal Processing, ICSP 2006 - Guilin, 中国 期限: 16 11月 2006 → 20 11月 2006 |
出版系列
姓名 | International Conference on Signal Processing Proceedings, ICSP |
---|---|
卷 | 3 |
会议
会议 | 8th International Conference on Signal Processing, ICSP 2006 |
---|---|
国家/地区 | 中国 |
市 | Guilin |
时期 | 16/11/06 → 20/11/06 |
指纹
探究 'Robust sequential learning algorithm for function approximation base on strong tracking filter' 的科研主题。它们共同构成独一无二的指纹。引用此
Kang, H., Shi, C., He, P., & Zhao, B. (2006). Robust sequential learning algorithm for function approximation base on strong tracking filter. 在 8th International Conference on Signal Processing, ICSP 2006 文章 4129219 (International Conference on Signal Processing Proceedings, ICSP; 卷 3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOSP.2006.345924