An augmented extended Kalman filter algorithm for complex-valued recurrent neural networks

被引：71
作者：
Goh, Su Lee [1 ]
Mandic, Danilo P. [1 ]
机构：
[1] Univ London Imperial Coll Sci Technol & Med, Dept Elect & Elect Engn, London SW7 2AZ, England
来源：
NEURAL COMPUTATION | 2007年 / 19卷 / 04期
关键词：
D O I：
10.1162/neco.2007.19.4.1039
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
An augmented complex-valued extended Kalman filter (ACEKF) algorithm for the class of nonlinear adaptive filters realized as fully connected recurrent neural networks is introduced. This is achieved based on some recent developments in the so-called augmented complex statistics and the use of general fully complex nonlinear activation functions within the neurons. This makes the ACEKF suitable for processing general complex-valued nonlinear and nonstationary signals and also bivariate signals with strong component correlations. Simulations on benchmark and real-world complex-valued signals support the approach.
引用
收藏
页码：1039 / 1055
页数：17
相关论文
共 31 条
[1]  
[Anonymous], 1987, THEORY DESIGN ADAPTI
[2]  
Anton H., 2003, CONT LINEAR ALGEBRA
[3]   Nonlinear adaptive prediction of speech with a pipelined recurrent neural network [J].
Baltersee, J ;
Chambers, JA .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (08) :2207-2216
[4]  
Brown R. G., 1997, INTRO RANDOM SIGNALS
[5]   A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification [J].
Feldkamp, LA ;
Puskorius, GV .
PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2259-2277
[6]   A complex-valued RTRL algorithm for recurrent neural networks [J].
Goh, SL ;
Mandic, DP .
NEURAL COMPUTATION, 2004, 16 (12) :2699-2713
[7]  
GOH SL, 2004, P 12 IEEE MED EL C M, V3, P1037
[8]  
Grewal M. S., 2001, KALMAN FILTERING THE, V4
[9]   NONLINEAR ADAPTIVE PREDICTION OF NONSTATIONARY SIGNALS [J].
HAYKIN, S ;
LI, L .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1995, 43 (02) :526-535
[10]  
Haykin S, 2001, ADAPT LEARN SYST SIG, P1
1234