摘要
函数的采样值进行预滤波处理后作为多子波神经网络的初始权值,明显地改善了多子波神经网络的逼近性能,提高了训练速度。
基金
国家自然科学基金(批准号:69772029)
国家"八六三"高技术资助项目
参考文献7
-
1[1]Poggio T,Girosi F.Networks for approximation and leaming.Proc IEEE,1990,78:1481
-
2[2]赵松年,熊小芸.子波变换与子波分析.北京:电子工业出版社,1997
-
3[3]Zhang J,Walter G G,Miao Y,et al.Wavelet neural networks for function networks for function leaming.IEEE Trans on Signal on Signal Processing,1995,43(6):1 485
-
4[4]Pati Y C,Krishnaprmad P S.Analysis and synlhesis of feedfonvard neural networks using discrete affine wavelet transfommtions.IEEE Trans Neural Net.,1993,4(1):73
-
5[5]Cohn,Daubechies I,Plonka G.Regularity of,larity of refinable function vectors.J Fourier Anal Appl,1997,3:295
-
6[6]Plonka G.Approximation order provided by refinable fumction vectors.Constr Approx,1997,13:221
-
7[7]Xia X G.A new prefilter design for discrete multiwavelet tramsforms.IEEE Trans Signal Process,1998,46:1558
同被引文献37
-
1Patel P,et al.Analysis of a simple successive interference cancellation scheme in a DS/CDMA system.IEEE JCAS,1994,12(5):796
-
2Divsalar D,Improved parallel interference cancellation for CDMA.IEEE Trans on Commun,1998,46(2):258
-
3Aazhang B,et al.Neural network for multiuser detection in CDMA communications.IEEE J Selection Areas Comm,1992,40(7):1212
-
4Pan J,et al.Construction of orthogonal multiwavelets with short se-quence via genetic algorithm.Progress in Natural Science,2000,10(4):294
-
5Chen J L,et al.Direct sequence code division multiple access based on multiwavelet packet transform.Progress in Natural Science,2001,11(9):715
-
6Honig M,et al.Blind adaptive multiuser detection.IEEE Trans on Information Theory,1995,41(4):944
-
7Wang X D.Blind multiuser detection:A Subspace approach.IEEE Trans on Information Theory,1998,44(1):91
-
8Lang T,et al.Blind identification and equalization based on second order statistics:A time domain approach.IEEE Trans on Informa-tion Theory,1994,40(3):340
-
9Michaela C.Estimation of parametric channel modelsin wireless communication.Networks,1998
-
10Shen J Q,et al.Direct blind MMSE channel equalization based on second order statistics.IEEE Trans on Signal Processing,2000,48(4):1015
二级引证文献5
-
1张旭秀,王培,邱天爽.基于改进信息最大化法的盲多用户检测[J].信息与控制,2008,37(5):556-559.
-
2何峰,丁宏,郑林华.基于WINC的自适应主分量提取的盲多用户检测算法[J].信号处理,2010,26(1):7-11.
-
3靳天玉,郭明超,饶增仁.一种基于全新算法的盲最佳多用户检测器[J].甘肃科学学报,2010,22(4):110-113.
-
4刘宁,张伟涛,楼顺天,冶继民.基于模糊逻辑的亚高斯与超高斯源混合盲分离[J].系统工程与电子技术,2011,33(7):1438-1442.
-
5朱孝龙,张贤达,冶继民.基于自然梯度的递归最小二乘盲信号分离[J].中国科学(E辑),2003,33(8):741-748. 被引量:15
-
1潘进,焦李成.多子波神经网络及其逼近性[J].电子学报,2000,28(10):60-64. 被引量:3
-
2朱晓铭,王士同.层次模糊系统的全局逼近性质及其与多子波神经网络关系研究[J].华东船舶工业学院学报,2002,16(1):23-28.
-
3唐玲,宋弘.一种基于最小Rayleigh熵的盲波束形成算法[J].舰船电子对抗,2010,33(5):54-56.
-
4张立毅,刘婷,孙云山,李锵.遗传算法优化神经网络权值盲均衡算法的研究[J].计算机工程与应用,2009,45(11):162-164. 被引量:14
-
5张科,赵桂芳,崔瑞青,袁祁刚.神经网络非均匀性校正算法中初始权值选取方法[J].激光与红外,2007,37(3):248-251. 被引量:5
-
6曹鹏,景占荣,姚晖.基于空域信息的稳健的宽带波束形成算法[J].计算机仿真,2012,29(8):127-130. 被引量:1
-
7唐玲,董思妤,陈玉梅,曾慧敏.半盲算法在自适应波束形成中的应用[J].四川理工学院学报(自然科学版),2009,22(2):87-90.
-
8尹洪伟,李国林,路翠华.改进的复值快速独立分量分析算法[J].探测与控制学报,2015,37(5):22-25. 被引量:3
-
9杨凯峰,牟莉,许亮.基于离散小波变换和RBF神经网络的说话人识别[J].西安理工大学学报,2011,27(3):368-372. 被引量:4
-
10黄小霞,符冉迪,石大维,范亚会.一种抗混叠移不变的Contourlet变换[J].宁波大学学报(理工版),2012,25(4):29-34. 被引量:1