Existence, learning, and replication of periodic motions in recurrent neural networks

被引：60
作者：
Ruiz, A
Owens, DH
Townley, S
机构：
[1] Univ Exeter, Ctr Syst & Control Engn, Exeter EX4 4QF, Devon, England
[2] Univ Exeter, Dept Math, Exeter EX4 4QE, Devon, England
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1998年 / 9卷 / 04期
基金：
英国工程与自然科学研究理事会;
关键词：
Hopf bifurcation; learning systems; neural networks; nonlinear dynamics;
D O I：
10.1109/72.701178
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A class of recurrent neural networks is shown to possess a stable limit cycle. A gradient type algorithm is used to modify the parameters of the network so that it learns and replicates autonomously a time varying periodic signal. The results are applied to controlling the repetitive motion of a two-link robot manipulator.
引用
收藏
页码：651 / 661
页数：11
相关论文
共 50 条
  • [1] Existence and learning of oscillations in recurrent neural networks
    Townley, S
    Ilchmann, A
    Weiss, MG
    Mcclements, W
    Ruiz, AC
    Owens, DH
    Prätzel-Wolters, D
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (01): : 205 - 214
  • [2] Existence and global exponential stability of periodic solutions of recurrent cellular neural networks with impulses and delays
    Guia, Zhanji
    Yang, Xiao-Song
    Ge, Weigao
    MATHEMATICS AND COMPUTERS IN SIMULATION, 2008, 79 (01) : 14 - 29
  • [3] Existence and global convergence of periodic solution of delayed neural networks
    Yuan, Zhaohui
    Yuan, Lifen
    MATHEMATICAL AND COMPUTER MODELLING, 2008, 48 (1-2) : 101 - 113
  • [4] Stability of Quasi-Periodic Orbits in Recurrent Neural Networks
    Marichal, R. L.
    Pineiro, J. D.
    Gonzalez, E. J.
    Torres, J.
    NEURAL PROCESSING LETTERS, 2010, 31 (03) : 269 - 281
  • [5] Stability of Quasi-Periodic Orbits in Recurrent Neural Networks
    R. L. Marichal
    J. D. Piñeiro
    E. J. González
    J. Torres
    Neural Processing Letters, 2010, 31 : 269 - 281
  • [6] Stable dynamic backpropagation learning in recurrent neural networks
    Jin, LA
    Gupta, MM
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (06): : 1321 - 1334
  • [7] Stability and existence of periodic solutions in inertial BAM neural networks with time delay
    Ke Yunquan
    Miao Chunfang
    NEURAL COMPUTING & APPLICATIONS, 2013, 23 (3-4) : 1089 - 1099
  • [8] Nonlinear dynamics and machine learning of recurrent spiking neural networks
    Maslennikov, O. V.
    Pugavko, M. M.
    Shchapin, D. S.
    Nekorkin, V. I.
    PHYSICS-USPEKHI, 2022, 65 (10) : 1020 - 1038
  • [9] Learning to recognize opinion targets using recurrent neural networks
    Liu, Yuanchao
    Wang, Junqi
    Wang, Xiaolong
    PATTERN RECOGNITION LETTERS, 2018, 106 : 41 - 46
  • [10] Stability and Existence of Periodic Solution for Delayed Reaction-Diffusion Cellular Neural Networks
    Pan, Jie
    Zhan, Yongxin
    PROCEEDINGS OF THE 7TH CONFERENCE ON BIOLOGICAL DYNAMIC SYSTEM AND STABILITY OF DIFFERENTIAL EQUATION, VOLS I AND II, 2010, : 976 - 979
12345