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
  • [41] Application of Kalman learning algorithm multilayer neural network to estimates of ore grades
    International Journal of Surface Mining, Reclamation and Environment, 12 (01): : 19 - 27
  • [42] Application of Kalman learning algorithm multilayer neural network to estimates of ore grades
    Div of Mining Eng, Lulea Univ of Technology, S-97187, Sweden
    International journal of surface mining & reclamation, 1998, 12 (01): : 19 - 27
  • [43] A LEARNING ALGORITHM FOR MULTILAYER NEURONLIKE NETWORK
    GAWRONSKI, RR
    ADVANCES IN ARTIFICIAL INTELLIGENCE RESEARCH, VOL 1, 1989, 1 : 159 - 176
  • [44] Adaptive Trajectory Tracking Algorithm of a Quadrotor with Sliding Mode Control and Multilayer Neural Network
    Niu, Kang
    Yang, Di
    Chen, Xi
    Wang, Rong
    Yu, Jianqiao
    COMPLEXITY, 2022, 2022
  • [45] Aerodynamic Parameter Fitting Based on BP Neural Network and Hybrid Optimization Algorithm
    Chao Tao
    Dong Chen
    Wang Songyan
    Yang Ming
    2014 11TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2014, : 4961 - 4964
  • [46] Hybrid neural network potential for multilayer graphene
    Wen, Mingjian
    Tadmor, Ellad B.
    PHYSICAL REVIEW B, 2019, 100 (19)
  • [47] A normalised backpropagation learning algorithm for multilayer feed-forward neural adaptive filters
    Hanna, AI
    Mandic, DP
    Razaz, M
    NEURAL NETWORKS FOR SIGNAL PROCESSING XI, 2001, : 63 - 72
  • [48] Convergence Properties of an Online Learning Algorithm in Neural Network Models of Complex Systems
    Azarskov, V. N.
    Nikolaienko, S. A.
    Zhiteckii, L. S.
    2013 IEEE 2ND INTERNATIONAL CONFERENCE ON ACTUAL PROBLEMS OF UNMANNED AIR VEHICLES DEVELOPMENTS (APUAVD), 2013, : 89 - 92
  • [49] Chaos algorithm of multilayer feedforward neural network
    Zhang, Jia-hai
    Xu, Yao-qun
    2006 CHINESE CONTROL CONFERENCE, VOLS 1-5, 2006, : 112 - +
  • [50] Chaos algorithm of multilayer feedforward neural network
    Xu, YQ
    Wang, SF
    Hao, YL
    Sun, F
    PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5, 2000, : 857 - 858