A STOCHASTIC NEWTON ALGORITHM WITH DATA-ADAPTIVE STEP SIZE

被引：3

作者：

DAVILA, CE

机构：

[1] Electrical Engineering Department, Southern Methodist University, Dallas

来源：

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING | 1990年 / 38卷 / 10期

关键词：

D O I：

10.1109/29.60110

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

A stochastic Newton algorithm for adaptive filtering is proposed which can be seen to be a generalization of the so-called normalized least mean-square (NLMS) algorithm. Expressions for the expected value of the algorithm weight error vector and second moment of the weight error-vector norm are derived and verified by computer simulation. Experimental results are given which demonstrate the improved convergence of the algorithm over the RLS algorithm after a large number of iterations. © 1990 IEEE

引用

页码：1796 / 1798

页数：3

共 12 条

[1] SHORT-TERM SEQUENTIAL REGRESSION ALGORITHM [J].

AHMED, N ;

HUMMELS, DR ;

UHL, ML ;

SOLDAN, DL .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1979, 27 (05) :453-457

[2]

ALBERT A. E., 1967, STOCHASTIC APPROXIMA

[3] ANALYSIS OF THE NORMALIZED LMS ALGORITHM WITH GAUSSIAN INPUTS [J].

BERSHAD, NJ .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1986, 34 (04) :793-806

[4] BEHAVIOR OF THE EPSILON-NORMALIZED LMS ALGORITHM WITH GAUSSIAN INPUTS [J].

BERSHAD, NJ .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1987, 35 (05) :636-644

[5] PERFORMANCE OF ADAPTIVE ESTIMATION ALGORITHMS IN DEPENDENT RANDOM-ENVIRONMENTS [J].

BITMEAD, RR ;

ANDERSON, BDO .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1980, 25 (04) :788-794

[6] FAST, RECURSIVE-LEAST-SQUARES TRANSVERSAL FILTERS FOR ADAPTIVE FILTERING [J].

CIOFFI, JM ;

KAILATH, T .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1984, 32 (02) :304-337

[7]

GRAUPE D, 1972, IDENTIFICATION SYSTE

[8]

Haykin S., 1986, ADAPTIVE FILTER THEO

[9]

Honig M. L., 1984, ADAPTIVE FILTERS STR

[10]

Ljung L, 1983, THEORY PRACTICE RECU

← 1 2 →