A general backpropagation algorithm for feedforward neural networks learning

被引：132

作者：

Yu, XH ^{[1
]}

Efe, MO

Kaynak, O

机构：

[1] Univ Cent Queensland, Fac Informat & Commun, Rockhampton, Qld 4072, Australia

[2] Carnegie Mellon Univ, Dept Elect & Comp Engn, Pittsburgh, PA 15213 USA

[3] Bogazici Univ, Dept Elect & Elect Engn, TR-80815 Istanbul, Turkey

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2002年 / 13卷 / 01期

关键词：

backpropagation; feedforward neural networks; stability; training;

D O I：

10.1109/72.977323

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this letter, a general backpropagation algorithm is proposed for feedforward neural networks learning with time varying inputs. The Lyapunov function approach is used to rigorously analyze the convergence of weights, with the use of the algorithm, toward minima of the error function. Sufficient conditions to guarantee the convergence of weights for time varying inputs are derived. It is shown that most commonly used backpropagation learning algorithms are special cases of the developed general algorithm.

引用

页码：251 / 254

页数：4

共 8 条

[1] STABILIZATION WITH RELAXED CONTROLS [J].

ARTSTEIN, Z .

NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 1983, 7 (11) :1163-1173

[2] A simplification of the backpropagation-through-time algorithm for optimal neurocontrol [J].

Bersini, H ;

Gorrini, V .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (02) :437-441

[3] On equilibria, stability, and instability of hopfield neural networks [J].

Guan, ZH ;

Chen, GR ;

Qin, Y .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02) :534-540

[4] TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM [J].

HAGAN, MT ;

MENHAJ, MB .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (06) :989-993

[5] Absolute exponential stability of neural networks with a general class of activation functions [J].

Liang, XB ;

Wang, J .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2000, 47 (08) :1258-1263

[6] A generalized learning paradigm exploiting the structure of feedforward neural networks [J].

Parisi, R ;

DiClaudio, ED ;

Orlandi, G ;

Rao, BD .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (06) :1450-1460

[7] On-line neural network learning algorithm with exponential convergence rate [J].

Zhao, Y .

ELECTRONICS LETTERS, 1996, 32 (15) :1381-1382

[8] Advanced neural-network training algorithm with reduced complexity based on Jacobian deficiency [J].

Zhou, G ;

Si, J .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (03) :448-453

← 1 →