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
  • [41] Stable reinforcement learning with recurrent neural networks
    James Nate KNIGHT
    Charles ANDERSON
    Journal of Control Theory and Applications, 2011, 9 (03) : 410 - 420
  • [42] Convergence result for learning in recurrent neural networks
    Kuan, Chung-Ming
    Hornik, Kurt
    White, Halbert
    Neural Computation, 1994, 6 (03)
  • [43] Learning to Adaptively Scale Recurrent Neural Networks
    Hu, Hao
    Wang, Liqiang
    Qi, Guo-Jun
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 3822 - 3829
  • [44] Learning Question Similarity with Recurrent Neural Networks
    Ye, Borui
    Feng, Guangyu
    Cheriton, David R.
    Cui, Anqi
    Li, Ming
    2017 IEEE INTERNATIONAL CONFERENCE ON BIG KNOWLEDGE (IEEE ICBK 2017), 2017, : 111 - 118
  • [45] A learning algorithm for improved recurrent neural networks
    Chen, CH
    Yu, LW
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 2198 - 2202
  • [46] Learning and bifurcation diagram of recurrent neural networks
    Sato, S
    Gohara, K
    PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 363 - 366
  • [47] Inaccessibility in online learning of recurrent neural networks
    Saito, A
    Taiji, M
    Ikegami, T
    PHYSICAL REVIEW LETTERS, 2004, 93 (16) : 168101 - 1
  • [48] Learning Morphological Transformations with Recurrent Neural Networks
    Biswas, Saurav
    Breuel, Thomas
    INNS CONFERENCE ON BIG DATA 2015 PROGRAM, 2015, 53 : 335 - 344
  • [49] Learning Multiple Timescales in Recurrent Neural Networks
    Alpay, Tayfun
    Heinrich, Stefan
    Wermter, Stefan
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT I, 2016, 9886 : 132 - 139
  • [50] Quantum recurrent neural networks for sequential learning
    Li, Yanan
    Wang, Zhimin
    Han, Rongbing
    Shi, Shangshang
    Li, Jiaxin
    Shang, Ruimin
    Zheng, Haiyong
    Zhong, Guoqiang
    Gu, Yongjian
    NEURAL NETWORKS, 2023, 166 : 148 - 161
12345