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
[41]   Design of Sports Training Method Based on Multilayer Feature Fusion and Deep Neural Network [J].
Sun, Xiaojuan ;
Saibon, Jamalsafri .
IEEE ACCESS, 2024, 12 :150204-150212
[42]   New approach to designing multilayer feedforward neural network architecture for modeling nonlinear restoring forces. II: Applications [J].
Pei, Jin-Song ;
Smyth, Andrew W. .
JOURNAL OF ENGINEERING MECHANICS, 2006, 132 (12) :1301-1312
[43]   New approach to designing multilayer feedforward neural network architecture for modeling nonlinear restoring forces. I: Formulation [J].
Pei, Jin-Song ;
Smyth, Andrew W. .
JOURNAL OF ENGINEERING MECHANICS, 2006, 132 (12) :1290-1300
[44]   An novel neural network training based on hybrid DE and BP [J].
Yuan, XH ;
Yuan, YB ;
Wang, C .
Artificial Intelligence Applications and Innovations II, 2005, 187 :477-481
[45]   A FAST NEURAL-NET TRAINING ALGORITHM AND ITS APPLICATION TO SPEECH CLASSIFICATION [J].
GHISELLICRIPPA, T ;
ELJAROUDI, A .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 1993, 6 (06) :549-557
[46]   PROGRESSIVE LEARNING ALGORITHM FOR GSN FEEDFORWARD NEURAL ARCHITECTURES [J].
DECARVALHO, A ;
FAIRHURST, MC ;
BISSET, DL .
ELECTRONICS LETTERS, 1994, 30 (06) :506-507
[47]   A NEW MULTILAYER FEEDFORWARD NETWORK BASED ON TRIMMED MEAN NEURON MODEL [J].
Yolcu, Ufuk ;
Bas, Eren ;
Egrioglu, Erol ;
Aladag, Cagdas Hakan .
NEURAL NETWORK WORLD, 2015, 25 (06) :587-602
[48]   Random Search Algorithm with Self-Learning for Neural Network Training [J].
V. A. Kostenko ;
L. E. Seleznev .
Optical Memory and Neural Networks, 2021, 30 :180-186
[49]   Random Search Algorithm with Self-Learning for Neural Network Training [J].
Kostenko, V. A. ;
Seleznev, L. E. .
OPTICAL MEMORY AND NEURAL NETWORKS, 2021, 30 (02) :180-186
[50]   A neural network training algorithm for singular perturbation boundary value problems [J].
Simos, T. E. ;
Famelis, Ioannis Th .
NEURAL COMPUTING & APPLICATIONS, 2022, 34 (01) :607-615
12345