A back-propagation algorithm with adaptive momentum factor

被引：0

作者：

Department of Applied Mathematics, Dalian University of Technology, Dalian 116024, China ^{[1
]}

不详 ^{[2
]}

机构：

来源：

Dalian Haishi Daxue Xuebao | 2008年 / 4卷 / 45-47+51期

关键词：

Momentum;

D O I：

暂无

中图分类号：

O3 [力学];

学科分类号：

08 ; 0801 ;

摘要：

A method was developed to adaptively determine the momentum factor of back-propagation (BP) algorithm to enhance the training speed of the neural networks. Taking the learning rate as constant, the algorithm adjusted the momentum factor according to the gradient of the error function with respect to the weight vector. Numerical experiments show that the proposed algorithm is effective for both the batch and online training. Moreover, it is superior to the BP algorithm with constant momentum factor in respect of convergence rate and stability.

引用

共 50 条

[41] Research the conditions of convergence of back-propagation learning algorithm
Jeenbekov, AA
Sarybaeva, AA
OPTOELECTRONIC AND HYBRID OPTICAL/DIGITAL SYSTEMS FOR IMAGE AND SIGNAL PROCESSING, 2000, 4148 : 12 - 18
[42] A ROBUST BACK-PROPAGATION LEARNING ALGORITHM FOR FUNCTION APPROXIMATION
CHEN, DS
JAIN, RC
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (03): : 467 - 479
[43] Parallel implementation of back-propagation algorithm in networks of workstations
Suresh, S
Omkar, SN
Mani, V
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2005, 16 (01) : 24 - 34
[44] Back-propagation of accuracy
Senashova, MY
Gorban, AN
Wunsch, DC
1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 1998 - 2001
[45] Back-propagation with Chaos
Fazayeli, Farideh
Wang, Lipo
Liu, Wen
2008 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND SIGNAL PROCESSING, VOLS 1 AND 2, 2007, : 5 - 8
[46] Beyond Back-Propagation Learning for Diabetic Detection: Convergence Comparison of Gradient Descent, Momentum and Adaptive Learning Rate
Endah, Sukmawati N.
Widodo, Aris P.
Fariq, Muhammad L.
Nadianada, Shavira I.
Maulana, Fadil
2017 1ST INTERNATIONAL CONFERENCE ON INFORMATICS AND COMPUTATIONAL SCIENCES (ICICOS), 2017, : 189 - 193
[47] Back-propagation is not efficient
Sima, J
NEURAL NETWORKS, 1996, 9 (06) : 1017 - 1023
[48] Sequential Back-Propagation
王晖
刘大有
王亚飞
Journal of Computer Science and Technology, 1994, (03) : 252 - 260
[49] MULTILAYER ADAPTIVE FILTERS TRAINED WITH BACK-PROPAGATION - A STATISTICAL APPROACH
KAHLA, MI
FARAJ, Z
CASTANIE, F
HOFFMANN, JC
SIGNAL PROCESSING, 1994, 40 (01) : 65 - 85
[50] Adaptive back-propagation in on-line learning of multilayer networks
West, AHL
Saad, D
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 323 - 329

← 1 2 3 4 5 →