Convergence of hybrid algorithm with adaptive learning parameter for multilayer neural network

被引:0
|
作者
Damak, Fadwa [1 ]
Ben Nasr, Mounir [1 ]
Chtourou, Mohamed [1 ]
机构
[1] ENIS, Dept Elect Engn, Sfax, Tunisia
关键词
Feedforward; neural network; Hybrid training; Adaptive learning rate; Lyapunov theory; TRAINING ALGORITHM; MOMENTUM;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
A new learning algorithm suited for training multilayered neural networks that we have named hybrid is hereby introduced. With this algorithm the weights of the hidden layer are adjusted using the Kohonen algorithm. While the weights of the output layer are trained using a gradient descent method with adaptive learning parameter based Lyapunov function. The effectiveness of the proposed approach is shown by the simulation results.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] Composite adaptive control with fast convergence for multilayer neural network
    Jiang, Tao
    Lin, Defu
    Song, Tao
    INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2019, 29 (13) : 4454 - 4471
  • [2] Parameter optimization algorithm with improved convergence properties for adaptive learning
    Magoulas, G. D.
    Vrahatis, M. N.
    IN THE FRONTIERS OF COMPUTATIONAL SCIENCE, 2005, 3 : 384 - 398
  • [3] Hybrid computation intelligent learning algorithm of global convergence for BP neural network based on genetic algorithm
    Xiong, Ling
    Zhao, Mingwang
    Wuhan Gangtie Xueyuan Xuebao/Journal of Wuhan Iron and Steel University, 2000, 23 (02): : 183 - 186
  • [4] The analysis of convergence of hybrid algorithm based on neural network and genetic algorithm
    Pan, MQ
    He, GP
    PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND BRAIN, VOLS 1-3, 2005, : 232 - 235
  • [5] SHORT-TERM LOAD FORECASTING USING A MULTILAYER NEURAL NETWORK WITH AN ADAPTIVE LEARNING ALGORITHM
    HO, KL
    HSU, YY
    YANG, CC
    IEEE TRANSACTIONS ON POWER SYSTEMS, 1992, 7 (01) : 141 - 149
  • [6] An adaptive learning algorithm for a wavelet neural network
    Bodyanskiy, Y
    Lamonova, N
    Pliss, I
    Vynokurova, O
    EXPERT SYSTEMS, 2005, 22 (05) : 235 - 240
  • [7] Learning algorithm study of adaptive neural network
    Lei, Ming
    Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering & Electronics, 1994, 16 (03):
  • [8] Blind Equalization Using a Hybrid Algorithm of Multilayer Neural Network
    梁启联
    HighTechnologyLetters, 1996, (01) : 47 - 50
  • [9] Blind equalization using a hybrid algorithm of multilayer neural network
    Beijing Univ of Posts &, Telecommunications, Beijing, China
    High Technol Letters, 1 (47-50):
  • [10] A hybrid genetic learning algorithm for Pi-sigma neural network and the analysis of its convergence
    Nie, Yong
    Deng, Wei
    ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 3, PROCEEDINGS, 2008, : 19 - 23