A Recurrent RBF Neural Network Based on Adaptive Optimum Steepest Descent Learning Algorithm

被引：0
|
作者：
Ma, Shijie [1 ,2 ]
Yang, Chili [1 ,2 ]
Qiao, Junfei [1 ,2 ]
机构：
[1] Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
[2] Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China
来源：
PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017) | 2017年
基金：
中国国家自然科学基金;
关键词：
Nonlinear system modeling; recurrent RBF neural network; AOSD learning algorithm; fast convergence; NONLINEAR-SYSTEMS; STABILITY;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In order to overcome the defects of gradient descent (GD) algorithm which lead to slow convergence and easy to fall into local minima, this paper proposes an adaptive optimum steepest descent (AOSD) learning algorithm which is used for the recurrent radial basis function (RRBF) neural network. Compared with traditional GD algorithm, the adaptive learning rate is integrated into the AOSD learning algorithm in order to accelerate the convergence speed of training algorithm and improve the network performance of nonlinear system modeling. Several comparisons show that the proposed RRBF has faster convergence speed and better prediction performance.
引用
收藏
页码：3942 / 3947
页数：6
相关论文
共 50 条
  • [31] RBF Neural Network Adaptive Sliding Mode Control Based on Genetic Algorithm Optimization
    Zhao Jie
    Han Long
    Ren Sijing
    [J]. PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, : 6772 - 6775
  • [32] STEEPEST DESCENT ALGORITHMS FOR NEURAL-NETWORK CONTROLLERS AND FILTERS
    PICHE, SW
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02): : 198 - 212
  • [33] Fast and scalable recurrent neural network learning based on stochastic meta-descent
    Liu, Zhenzhen
    Elhanany, Itamar
    [J]. 2007 AMERICAN CONTROL CONFERENCE, VOLS 1-13, 2007, : 3844 - 3849
  • [34] NEW ADAPTIVE ALGORITHMS BASED ON THE METHOD OF STEEPEST DESCENT
    ARUNACHALAM, KG
    CHESMORE, ED
    [J]. INTERNATIONAL JOURNAL OF ELECTRONICS, 1993, 74 (01) : 1 - 19
  • [35] A Virtual Network Embedding Algorithm Based on RBF Neural Network
    Zhang, Hui
    Zheng, Xiangwei
    Tian, Jie
    Xue, Qingshui
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE) AND IEEE/IFIP INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING (EUC), VOL 1, 2017, : 393 - 396
  • [36] Intrusion detection based on adaptive RBF neural network
    Zhong, Jiang
    Li, Zhiguo
    Feng, Yong
    Ye, Cunxiao
    [J]. ISDA 2006: SIXTH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, VOL 2, 2006, : 1081 - +
  • [37] Enriching Elementary School Mathematical Learning with the Steepest Descent Algorithm
    Araya, Roberto
    [J]. MATHEMATICS, 2021, 9 (11)
  • [38] Hybrid hyperplane gradient learning algorithm for RBF neural network
    Ma, Miao-li
    Huang, Zhe-kun
    Liao, Yu-hang
    Zhou, Li-yi
    Jia, Li-jie
    Liang, Cun-zhen
    Guo, Zhi-jun
    [J]. NEUROCOMPUTING, 2024, 587
  • [39] Design and Testing of an MPPT Algorithm Using an Intelligent RBF Neural Network and Optimum Relation Based Strategy
    Rahman, M. M. Atiqur
    Rahim, A. H. M. A.
    [J]. 2020 IEEE REGION 10 SYMPOSIUM (TENSYMP) - TECHNOLOGY FOR IMPACTFUL SUSTAINABLE DEVELOPMENT, 2020, : 1245 - 1248
  • [40] Design of RBF neural network based on SAPSO algorithm
    Zhang, Wei
    Huang, Wei-Min
    [J]. Kongzhi yu Juece/Control and Decision, 2021, 36 (09): : 2305 - 2312
12345