A modified gradient-based neuro-fuzzy learning algorithm and its convergence

被引：70
|
作者：
Wu, Wei [1 ]
Li, Long [1 ]
Yang, Jie [1 ]
Liu, Yan [2 ]
机构：
[1] Dalian Univ Technol, Dept Appl Math, Dalian 116024, Peoples R China
[2] Dalian Polytech Univ, Dept Appl Math, Dalian 116034, Peoples R China
来源：
INFORMATION SCIENCES | 2010年 / 180卷 / 09期
基金：
中国国家自然科学基金;
关键词：
Zero-order Takagi-Sugeno inference system; Modified gradient-based neuro-fuzzy learning algorithm; Convergence; Constant learning rate; Gaussian membership function; INFERENCE SYSTEM; IDENTIFICATION; NETWORK;
D O I：
10.1016/j.ins.2009.12.030
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Neuro-fuzzy approach is known to provide an adaptive method to generate or tune fuzzy rules for fuzzy systems. In this paper, a modified gradient-based neuro-fuzzy learning algorithm is proposed for zero-order Takagi-Sugeno inference systems. This modified algorithm, compared with conventional gradient-based neuro-fuzzy learning algorithm, reduces the cost of calculating the gradient of the error function and improves the learning efficiency. Some weak and strong convergence results for this algorithm are proved, indicating that the gradient of the error function goes to zero and the fuzzy parameter sequence goes to a fixed value, respectively. A constant learning rate is used. Some conditions for the constant learning rate to guarantee the convergence are specified. Numerical examples are provided to support the theoretical findings. (C) 2010 Elsevier Inc. All rights reserved.
引用
收藏
页码：1630 / 1642
页数：13
相关论文
共 50 条
  • [1] A Split-Complex Valued Gradient-Based Descent Neuro-Fuzzy Algorithm for TS System and Its Convergence
    Liu, Yan
    Yang, Dakun
    Li, Long
    Yang, Jie
    [J]. NEURAL PROCESSING LETTERS, 2019, 50 (02) : 1589 - 1609
  • [2] A Split-Complex Valued Gradient-Based Descent Neuro-Fuzzy Algorithm for TS System and Its Convergence
    Yan Liu
    Dakun Yang
    Long Li
    Jie Yang
    [J]. Neural Processing Letters, 2019, 50 : 1589 - 1609
  • [3] A Polak-Ribiere-Polyak Conjugate Gradient-Based Neuro-Fuzzy Network and Its Convergence
    Gao, Tao
    Wang, Jian
    Zhang, Bingjie
    Zhang, Huaqing
    Ren, Peng
    Pal, Nikhil R.
    [J]. IEEE ACCESS, 2018, 6 : 41551 - 41565
  • [4] An online gradient-based parameter identification algorithm for the neuro-fuzzy systems
    Li, Long
    Long, Zuqiang
    Ying, Hao
    Qiao, Zhijun
    [J]. FUZZY SETS AND SYSTEMS, 2022, 426 : 27 - 45
  • [5] A Modified Gradient-Based Neuro-Fuzzy Learning Algorithm for Pi-Sigma Network Based on First-Order Takagi-Sugeno System
    Yan LIU
    Jie YANG
    Dakun YANG
    Wei WU
    [J]. Journal of Mathematical Research with Applications, 2014, 34 (01) : 114 - 126
  • [6] Gradient-based back-propagation dynamical iterative learning scheme for the neuro-fuzzy inference system
    Nejad, Hadi Chahkandi
    Farshad, Mohsen
    Rahatabad, Fereidoun Nowshiravan
    Khayat, Omid
    [J]. EXPERT SYSTEMS, 2016, 33 (01) : 70 - 76
  • [7] Convergence of Recurrent Neuro-Fuzzy Value-Gradient Learning With and Without an Actor
    Al-Dabooni, Seaar
    Wunsch, Donald
    [J]. IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2020, 28 (04) : 658 - 672
  • [8] Convergence analysis of the batch gradient-based neuro-fuzzy learning algorithm with smoothing L1/2 regularization for the first-order Takagi-Sugeno system
    Liu, Yan
    Yang, Dakun
    [J]. FUZZY SETS AND SYSTEMS, 2017, 319 : 28 - 49
  • [9] WAVELET NEURO-FUZZY MODEL WITH HYBRID LEARNING ALGORITHM OF GRADIENT DESCENT AND GENETIC ALGORITHM
    Banakar, Ahmad
    Azeem, Mohammad Fazle
    [J]. INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, 2011, 9 (02) : 333 - 359
  • [10] On designing of learning rates in the neuro-fuzzy learning algorithm
    Shi, Y
    Mizumoto, M
    Shi, P
    [J]. ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 1575 - 1578
12345