TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM

被引：5495
|
作者：
HAGAN, MT
MENHAJ, MB
机构：
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1994年 / 5卷 / 06期
关键词：
D O I：
10.1109/72.329697
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the-other techniques when the network contains no more than a few hundred weights.
引用
收藏
页码：989 / 993
页数：5
相关论文
共 50 条
  • [41] Training Feedforward Neural Networks Using an Enhanced Marine Predators Algorithm
    Zhang, Jinzhong
    Xu, Yubao
    PROCESSES, 2023, 11 (03)
  • [42] Training Feedforward Neural Networks Using Symbiotic Organisms Search Algorithm
    Wu, Haizhou
    Zhou, Yongquan
    Luo, Qifang
    Basset, Mohamed Abdel
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2016, 2016
  • [43] Composite squared-error algorithm for training feedforward neural networks
    Gonzaga, D
    de Campos, MLR
    Netto, SL
    1998 IEEE SYMPOSIUM ON ADVANCES IN DIGITAL FILTERING AND SIGNAL PROCESSING, 1998, : 116 - 120
  • [44] A fuzzy neighborhood-based training algorithm for feedforward neural networks
    Ben Nasr, Mounir
    Chtourou, Mohamed
    NEURAL COMPUTING & APPLICATIONS, 2009, 18 (02): : 127 - 133
  • [45] An efficient EM-based training algorithm for feedforward neural networks
    Ma, S
    Ji, CY
    Farmer, J
    NEURAL NETWORKS, 1997, 10 (02) : 243 - 256
  • [46] Am activation function adapting training algorithm for sigmoidal feedforward networks
    Chandra, P
    Singh, Y
    NEUROCOMPUTING, 2004, 61 : 429 - 437
  • [47] ON TRAINING FEEDFORWARD NEURAL NETWORKS
    KAK, S
    PRAMANA-JOURNAL OF PHYSICS, 1993, 40 (01): : 35 - 42
  • [48] Levenberg-Marquardt training for modular networks
    Fun, MH
    Hagan, MT
    ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 468 - 473
  • [49] A Self-Adaptive Hybrid Bat Algorithm for Training Feedforward Neural Networks
    Bousmaha, Rabab
    Hamou, Reda Mohamed
    Amine, Abdelmalek
    INTERNATIONAL JOURNAL OF SWARM INTELLIGENCE RESEARCH, 2021, 12 (03) : 149 - 171
  • [50] A unified approach on fast training of feedforward and recurrent networks using EM algorithm
    Ma, S
    Ji, CY
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (08) : 2270 - 2274
12345