NOVEL FAST TRAINING ALGORITHM FOR MULTILAYER FEEDFORWARD NEURAL NETWORK

被引：9
作者：
PARK, DJ
JUN, BE
KIM, JH
机构：
[1] Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Taejon 305-701, 373-1 Kusong-dong, Yusung-gu
来源：
ELECTRONICS LETTERS | 1992年 / 28卷 / 06期
关键词：
NEURAL NETWORKS; ALGORITHMS;
D O I：
10.1049/el:19920343
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：
A new fast learning algorithm for a multilayer feedforward neural network is presented. The new algorithm, based on an innovative variable step size and gradient averaging, has excellent properties to overcome major drawbacks of the backpropagation algorithm and shows high convergence speed. The improved performance of the new algorithm in comparison with other algorithms is verified via computer simulations.
引用
收藏
页码：543 / 545
页数：3
相关论文
共 50 条
[21]   MULTIPLIERLESS MULTILAYER FEEDFORWARD NEURAL-NETWORK DESIGN SUITABLE FOR CONTINUOUS INPUT-OUTPUT MAPPING [J].
KWAN, HK ;
TANG, CZ .
ELECTRONICS LETTERS, 1993, 29 (14) :1259-1260
[22]   Local coupled feedforward neural network [J].
Sun, Jianye .
NEURAL NETWORKS, 2010, 23 (01) :108-113
[23]   Testing Feedforward Neural Networks Training Programs [J].
Ben Braiek, Houssem ;
Khomh, Foutse .
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2023, 32 (04)
[24]   Shape from focus using multilayer feedforward neural networks [J].
Asif, M ;
Choi, TS .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2001, 10 (11) :1670-1675
[25]   Shape from focus using multilayer feedforward neural networks [J].
Asif, M ;
Choi, TS .
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2000, E83D (04) :946-949
[26]   Properties of a Batch Training Algorithm for Feedforward Networks [J].
Robinson, Melvin D. ;
Manry, Michael T. ;
Malalur, Sanjeev S. ;
Yu, Changhua .
NEURAL PROCESSING LETTERS, 2017, 45 (03) :841-854
[27]   A fast learning algorithm of neural network with tunable activation function [J].
Yanjun Shen ;
Bingwen Wang .
Science in China Series F: Information Sciences, 2004, 47 :126-136
[28]   A fast learning algorithm of neural network with tunable activation function [J].
SHEN Yanjun WANG BingwenDepartment of Control Science and Engineering University of Science and Technology Wuhan China .
ScienceinChina(SeriesF:InformationSciences), 2004, (01) :126-136
[29]   A fast learning algorithm of neural network with tunable activation function [J].
Shen, YJ ;
Wang, BW .
SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES, 2004, 47 (01) :126-136
[30]   A novel neural network training framework with data assimilation [J].
Chong Chen ;
Yixuan Dou ;
Jie Chen ;
Yaru Xue .
The Journal of Supercomputing, 2022, 78 :19020-19045
12345