AN ADAPTIVE TRAINING ALGORITHM FOR BACKPROPAGATION NEURAL NETWORKS

被引：31

作者：

HSIN, HC ^{[1
]}

LI, CC ^{[1
]}

SUN, MG ^{[1
]}

SCLABASSI, RJ ^{[1
]}

机构：

[1] UNIV PITTSBURGH,DEPT NEUROL SURG,PITTSBURGH,PA 15261

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS | 1995年 / 25卷 / 03期

关键词：

D O I：

10.1109/21.364864

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A dynamic learning rate for back-propagation training of artificial neural networks is proposed as a weighted average of direction cosines of the incremental weight vectors of the current and previous steps. Experiments on training an EEG-based sleep state pattern recognition scheme have demonstrated its improved performance.

引用

页码：512 / 514

页数：3

共 15 条

[1]

[Anonymous], 1987, LEARNING INTERNAL RE

[2]

BECKER S, 1988, 1988 P CONN MOD SUMM, P29

[3] ENHANCED TRAINING ALGORITHMS, AND INTEGRATED TRAINING ARCHITECTURE SELECTION FOR MULTILAYER PERCEPTRON NETWORKS [J].

BELLO, MG .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (06) :864-875

[4] FAST TRAINING ALGORITHMS FOR MULTILAYER NEURAL NETS [J].

BRENT, RP .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (03) :346-354

[5]

FAHLMAN SE, 1988, 1988 P CONN MOD SUMM, P38

[6]

FRANZANI MA, 1987, 9 ANN C ENGMED BIOL, P1702

[7] A NEW BACK-PROPAGATION ALGORITHM WITH COUPLED NEURON [J].

FUKUMI, M ;

OMATU, S .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (05) :535-538

[8]

KUAN CM, 1991, IEEE T NEURAL NETWOR, V2, P384

[9]

Lippmann R. P., 1988, Computer Architecture News, V16, P7, DOI [10.1109/MASSP.1987.1165576, 10.1145/44571.44572]

[10] AN ADAPTIVELY TRAINED NEURAL NETWORK [J].

PARK, DC ;

ELSHARKAWI, MA ;

MARKS, RJ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (03) :334-345

← 1 2 →