Parameter Tuning of MLP Neural Network Using Genetic Algorithms

被引:0
作者
Er, Meng Joo [1 ]
Liu, Fan [1 ]
机构
[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
来源
SIXTH INTERNATIONAL SYMPOSIUM ON NEURAL NETWORKS (ISNN 2009) | 2009年 / 56卷
关键词
Genetic algorithms; Backpropagation; Function approximation; Nonlinear dynamic system identification; BUSINESS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, a hybrid learning algorithm for a Multilayer Percept-rons (MLP) Neural Network using Genetic Algorithms (GA) is proposed. This hybrid learning algorithm has two steps: First, all the parameters (weights and biases) of the initial neural network are encoded to form a long chromosome and tuned by the GA. Second, as a result of the GA process, a quasi-Newton method called BFGS method is applied to train the neural network. Simulation studies on function approximation and nonlinear dynamic system identification are presented to illustrate the performance of the proposed learning algorithm.
引用
收藏
页码:121 / 130
页数:10
相关论文
共 50 条
  • [31] New classification technique using neural networks and genetic algorithms
    Bailoul, Charaf Eddine
    Alaa, Nour Eddine
    ANNALS OF THE UNIVERSITY OF CRAIOVA-MATHEMATICS AND COMPUTER SCIENCE SERIES, 2019, 46 (02): : 433 - 444
  • [32] Highway traffic prediction with neural network and genetic algorithms
    Wang, Y
    Wang, H
    Xia, LM
    2005 IEEE International Conference on Vehicular Electronics and Safety Proceedings, 2005, : 211 - 216
  • [33] Bayesian network as an adaptive parameter setting approach for genetic algorithms
    Guillaume Corriveau
    Raynald Guilbault
    Antoine Tahan
    Robert Sabourin
    Complex & Intelligent Systems, 2016, 2 (1) : 1 - 22
  • [34] Diagonal recurrent neural network based on genetic algorithms
    Du Yan-chun
    Ll Yi-bin
    Wang Gui-yue
    Proceedings of the 2007 Chinese Control and Decision Conference, 2007, : 443 - 446
  • [35] Optimization of E.Coli heat shock response parameter tuning using distributed and integrated genetic algorithms
    Tanaka, S
    Kurata, H
    Ohashi, T
    2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7, 2004, : 1243 - 1248
  • [36] COMPARING EVOLUTIONARY ALGORITHMS ON TUNING THE PARAMETERS OF FUZZY WAVELET NEURAL NETWORK
    Khedri, P. Arab
    Eftekhari, M.
    Maazallahi, R.
    IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF ELECTRICAL ENGINEERING, 2013, 37 (E2) : 193 - 198
  • [37] Neural network algorithms for tuning of fuzzy certainty factor expert systems
    Jafari, S
    Shabaninia, F
    Nava, PA
    MULTIMEDIA, IMAGE PROCESSING AND SOFT COMPUTING: TRENDS, PRINCIPLES AND APPLICATIONS, 2002, 13 : 95 - 100
  • [38] Harmonic reduction in PWM AC voltage controller using genetic algorithms and neural network
    Kaitwanidvilai, Somyot
    Piyarungsan, Pairoj
    IMECS 2007: INTERNATIONAL MULTICONFERENCE OF ENGINEERS AND COMPUTER SCIENTISTS, VOLS I AND II, 2007, : 1674 - +
  • [39] Analysing blast furnace data using evolutionary neural network and multiobjective genetic algorithms
    Agarwal, A.
    Tewary, U.
    Pettersson, F.
    Das, S.
    Saxen, H.
    Chakraborti, N.
    IRONMAKING & STEELMAKING, 2010, 37 (05) : 353 - 359
  • [40] Segmentation of MR and CT Images Using a Hybrid Neural Network Trained by Genetic Algorithms
    Zümray Dokur
    Neural Processing Letters, 2002, 16 : 211 - 225