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

页码：609 / 615

页数：7

共 50 条

[41] Training recurrent neural networks via dynamical trajectory-based optimization
Khodabandehlou, Hamid
Fadali, M. Sami
NEUROCOMPUTING, 2019, 368 : 1 - 10
[42] Effect of Alzheimer's disease on the dynamical and computational characteristics of recurrent neural networks
Claudia Bachmann
Tom Tetzlaff
Susanne Kunkel
Philipp Bamberger
Abigail Morrison
BMC Neuroscience, 14 (Suppl 1)
[43] Identification of nonlinear dynamical systems by recurrent high-order neural networks
Kuroe, Y
Ikeda, H
Mori, T
SMC '97 CONFERENCE PROCEEDINGS - 1997 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: CONFERENCE THEME: COMPUTATIONAL CYBERNETICS AND SIMULATION, 1997, : 70 - 75
[44] APPROXIMATION OF DYNAMICAL-SYSTEMS BY CONTINUOUS-TIME RECURRENT NEURAL NETWORKS
FUNAHASHI, K
NAKAMURA, Y
NEURAL NETWORKS, 1993, 6 (06) : 801 - 806
[45] Sufficient conditions for error back flow convergence in dynamical recurrent neural networks
Aussem, A
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL IV, 2000, : 577 - 582
[46] Deciphering Dynamical Nonlinearities in Short Time Series Using Recurrent Neural Networks
Nagarajan, Radhakrishnan
SCIENTIFIC REPORTS, 2019, 9 (1)
[47] Equivalence in knowledge representation: Automata, recurrent neural networks, and dynamical fuzzy systems
Giles, CL
Omlin, CW
Thornber, KK
PROCEEDINGS OF THE IEEE, 1999, 87 (09) : 1623 - 1640
[48] Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
Smith, Jimmy T. H.
Linderman, Scott W.
Sussillo, David
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[49] DYNAMICAL RECURRENT NEURAL NETWORKS - TOWARDS ENVIRONMENTAL TIME-SERIES PREDICTION
AUSSEM, A
MURTAGH, F
SARAZIN, M
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 1995, 6 (02) : 145 - 170
[50] TRAINING RECURRENT NEURAL NETWORKS - WHY AND HOW - AN ILLUSTRATION IN DYNAMICAL PROCESS MODELING
NERRAND, O
ROUSSELRAGOT, P
URBANI, D
PERSONNAZ, L
DREYFUS, G
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02): : 178 - 184

← 1 2 3 4 5 →