Dynamical features simulated by recurrent neural networks

被引:7
|
作者
Botelho, F [1 ]
机构
[1] Univ Memphis, Dept Math Sci, Memphis, TN 38152 USA
关键词
neural network; brain-state-in-a box;
D O I
10.1016/S0893-6080(99)00026-X
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The evolution of two-dimensional neural network models with rank one connecting matrices and saturated linear transfer functions is dynamically equivalent to that of piecewise linear maps on an interval. It is shown that their iterative behavior ranges from being highly predictable, where almost every orbit accumulates to an attracting fixed point, to the existence of chaotic regions with cycles of arbitrarily large period. (C) 1999 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:609 / 615
页数:7
相关论文
共 50 条
  • [1] Dynamical approximation by recurrent neural networks
    Garzon, M
    Botelho, F
    NEUROCOMPUTING, 1999, 29 (1-3) : 25 - 46
  • [2] Dynamical consistent recurrent neural networks
    Zimmermann, HG
    Grothmann, R
    Schäfer, AM
    Tietz, C
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 1537 - 1541
  • [3] Modeling dynamical systems by recurrent neural networks
    Zimmermann, HG
    Neuneier, R
    DATA MINING II, 2000, 2 : 557 - 566
  • [4] Dynamical Systems Produced by Recurrent Neural Networks
    Kimura, Masahiro
    Nakano, Ryohei
    Systems and Computers in Japan, 2000, 31 (04) : 77 - 86
  • [5] Dynamic recurrent neural networks: A dynamical analysis
    Draye, JPS
    Pavisic, DA
    Cheron, GA
    Libert, GA
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1996, 26 (05): : 692 - 706
  • [6] Dynamic recurrent neural networks: a dynamical analysis
    Faculte Polytechnique de Mons, Mons, Belgium
    IEEE Trans Syst Man Cybern Part B Cybern, 5 (692-706):
  • [7] Dynamical recurrent neural networks towards prediction and modeling of dynamical systems
    Aussem, A
    NEUROCOMPUTING, 1999, 28 : 207 - 232
  • [8] Dynamical Hyperspectral Unmixing With Variational Recurrent Neural Networks
    Borsoi, Ricardo A. A.
    Imbiriba, Tales
    Closas, Pau
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 2279 - 2294
  • [9] Synthesis of recurrent neural networks for dynamical system simulation
    Trischler, Adam P.
    D'Eleuterio, Gabriele M. T.
    NEURAL NETWORKS, 2016, 80 : 67 - 78
  • [10] Recurrent neural networks for partially observed dynamical systems
    Bhat, Uttam
    Munch, Stephan B.
    PHYSICAL REVIEW E, 2022, 105 (04)