计算机科学 ›› 2014, Vol. 41 ›› Issue (7): 266-269.doi: 10.11896/j.issn.1002-137X.2014.07.055
曾祥萍,金炜东,赵海全,李天瑞
ZENG Xiang-ping,JIN Wei-dong,ZHAO Hai-quan and LI Tian-rui
摘要： 传统的随机梯度算法由于采用基于二阶统计量的平方误差代价函数,因此含有的信息量较少,难以实现更高的精度。针对此问题,以基于高阶统计量的指数平方误差作为代价函数,结合基于两层RBF网络凸组合的非线性自适应滤波器,提出了最小指数平方误差自适应学习算法。非线性系统辨识和非线性信道均衡的实验仿真结果表明,该改进算法的收敛性能明显优于传统的随机梯度算法。
| [1] Park J,Sandberg I W．Universal approximation using radial-ba-sis-function networks[J]．Neural Comput,1991,3(2):246-257 [2] Kassam S A,Cha I．Radial basis function networks in nonlinear signal processing applications[C]∥Proceedings of the 11th Asilomar Conference on Signals,Systems and Computers．1993:1021-1025 [3] Chng E S,Chen S,Mulgrew B．Gradient radial basis function networks for nonlinear and nonstationary time series prediction[J]．IEEE Transactions on Neural Networks,1996,7(1):190-194 [4] Chen S,Cowan C F N,Grant P M．Orthogonal least squares learning algorithm for radial basis function networks[J]．IEEE Transactions on Neural Networks,1991,2(2):302-309 [5] Kadirkamanathan V,Niranjan M．A function estimation ap-proach to sequential learning with neural networks[J]．Neural Comput,1993,5(6):954-975 [6] Huang G-B,Saratchandran P,Sundararajan N．An efficient se-quential learning algorithm for growing and pruning RBF(GAP-RBF) networks[J]．IEEE Transactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2004,34(6):2284-2292 [7] Zeng X,Zhao H,Jin W,et al.Identification of nonlinear dynamic systems using convex combinations of multiple adaptive radius basis function networks[J]．Measurement,2013,46(1):628-638 [8] Cha I,Kassam S A．Channel equalization using adaptive complex radial basis function networks[J]．IEEE Journal on Selected Areas in Communications,1995,13(1):122-131 [9] Andersson P．Adaptive forgetting in recursive identificationthrough multiple models[J]．International Journal of Control,1985,42(5):1175-1193 [10] Niedzwiecki M．Multiple-model approach to finite memory adaptive filtering[J]．IEEE Transactions on Signal Processing,1992,40(2):470-473 [11] Zeng X,Zhao H,Jin W．Adaptive Convex Combination of Two RBF Networks and its Application to Nonlinear System Identification[J]．Advanced Materials Research,2012,562:1697-1701 [12] Boukis C,Mandic D P,Constantinides A G．A class of stochastic gradient algorithms with exponentiated error cost functions[J]．Digital Signal Processing,2009,19(2):201-212 [13] Lee J,Beach C,Tepedelenlioglu N．A practical radial basis function equalizer[J]．IEEE Transactions on Neural Networks,1999,10(2):450-455 |
| No related articles found! |
|
||
首页