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
来源：
NEURAL NETWORKS | 1999年 / 12卷 / 4-5期
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
  • [21] Learning Stable Recurrent Excitation in Simulated Biological Neural Networks
    Teichmann, Michael
    Hamker, Fred H.
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2017, PT I, 2017, 10613 : 449 - 450
  • [22] Robust Pinning Control of Complex Dynamical Networks using Recurrent Neural Networks
    Sanchez, Edgar N.
    Rodriguez, David I.
    2014 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN CONTROL AND AUTOMATION (CICA), 2014, : 83 - 89
  • [23] Application of neural networks to identify features of dynamical grounding systems
    de Souza, AN
    da Silva, IN
    Ulson, JAC
    IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 2093 - 2097
  • [24] Dynamical time series emb e ddings in recurrent neural networks
    Uribarri, Gonzalo
    Mindlin, Gabriel B.
    CHAOS SOLITONS & FRACTALS, 2022, 154
  • [25] ODE-RU: a dynamical system view on recurrent neural networks
    Meng, Pinchao
    Wang, Xinyu
    Yin, Weishi
    ELECTRONIC RESEARCH ARCHIVE, 2022, 30 (01): : 257 - 271
  • [26] Dynamical complexity and computation in recurrent neural networks beyond their fixed point
    Bicky A. Marquez
    Laurent Larger
    Maxime Jacquot
    Yanne K. Chembo
    Daniel Brunner
    Scientific Reports, 8
  • [27] Reinforcement Learning for Central Pattern Generation in Dynamical Recurrent Neural Networks
    Yoder, Jason A.
    Anderson, Cooper B.
    Wang, Cehong
    Izquierdo, Eduardo J.
    FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2022, 16
  • [28] Dynamical complexity and computation in recurrent neural networks beyond their fixed point
    Marquez, Bicky A.
    Larger, Laurent
    Jacquot, Maxime
    Chembo, Yanne K.
    Brunner, Daniel
    SCIENTIFIC REPORTS, 2018, 8
  • [29] PROCESS OF LEARNING DISCRETE DYNAMICAL-SYSTEMS BY RECURRENT NEURAL NETWORKS
    NAKAJIMA, H
    KODA, T
    UDA, Y
    ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 1994, 77 (09): : 12 - 21
  • [30] Sufficient conditions for error backflow convergence in dynamical recurrent neural networks
    Aussem, A
    NEURAL COMPUTATION, 2002, 14 (08) : 1907 - 1927
12345