ON THE COMPLEX BACKPROPAGATION ALGORITHM

被引：225

作者：

BENVENUTO, N ^{[1
]}

PIAZZA, F ^{[1
]}

机构：

[1] UNIV ANCONA,DIPARTIMENTO ELETTR & AUTOMAT,I-60100 ANCONA,ITALY

来源：

IEEE TRANSACTIONS ON SIGNAL PROCESSING | 1992年 / 40卷 / 04期

关键词：

D O I：

10.1109/78.127967

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this correspondence a recursive algorithm for updating the coefficients of a neural network structure for complex signals is presented. Various complex activation functions are considered and a practical definition is proposed. The method, associated to a mean-square-error criterion, yields the complex form of the conventional backpropagation algorithm.

引用

页码：967 / 968

页数：2

共 10 条

[1]

[Anonymous], 1974, MATH ANAL

[2]

BENVENUTO N, 1991, MAY P INT C ASSP TOR, P1521

[3]

BENVENUTO N, 1991, JUN P INT C ART NEUR, P1177

[4]

CLARKE TL, 1990, JUN P INT JOINT C NE, P435

[5]

KIM MS, 1990, JUN P INT JOINT C NE, P27

[6]

Rumelhart DE, 1986, ENCY DATABASE SYST, P45

[7] COMPLEX LMS ALGORITHM [J].

WIDROW, B ;

MCCOOL, J ;

BALL, M .

PROCEEDINGS OF THE IEEE, 1975, 63 (04) :719-720

[8] 30 YEARS OF ADAPTIVE NEURAL NETWORKS - PERCEPTRON, MADALINE, AND BACKPROPAGATION [J].

WIDROW, B ;

LEHR, MA .

PROCEEDINGS OF THE IEEE, 1990, 78 (09) :1415-1442

[9]

1990, P IEEE 2, V78

[10]

1990, P IEEE 1, V78

← 1 →