Effect of Weighting Parameters on Dynamical Behavior of Hopfield Neural Networks with Logistic map Activation Functions

被引：0

作者：

Mahdavi, Nariman ^{[1
]}

Menhaj, M. B. ^{[1
]}

Afshar, A. ^{[1
]}

机构：

[1] Amir Kabir Univ Technol, Dept Elect Engn, Tehran, Iran

来源：

CICA: 2009 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN CONTROL AND AUTOMATION | 2009年

关键词：

PULSE-COUPLED NETWORK; BASIC DYNAMICS; CHAOS; OSCILLATIONS;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In ANN terminology, the synaptic connections are the weights of the neural networks and can be seen as an interaction between neurons. In this paper, we consider two simple neurons which have both self-coupling and non-invertible activation functions. Our studies on these interactions lead to different dynamical behaviors of the network. We show that they can be used as a means of chaos generation or suppression to neuron's outputs when more adaptability or stability is required. This idea may be further used for chaos synchronization of neuron's outputs.

引用

页码：57 / 61

页数：5

共 50 条

[41] Simple activation functions for neural and fuzzy neural networks
Mendil, Boubekeur
Benmahammed, K.
Proceedings - IEEE International Symposium on Circuits and Systems, 1999, 5
[42] Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions
Mathias, Amanda C.
Rech, Paulo C.
NEURAL NETWORKS, 2012, 34 : 42 - 45
[43] Memristive Hopfield neural network dynamics with heterogeneous activation functions and its application
Deng, Quanli
Wang, Chunhua
Lin, Hairong
CHAOS SOLITONS & FRACTALS, 2024, 178
[44] Dynamic behavior of discrete Hopfield neural networks with time-delay
Ma, RN
Xi, YM
Lei, SP
CHINESE JOURNAL OF ELECTRONICS, 2005, 14 (02): : 187 - 191
[45] Dynamical Behaviors of Multiple Equilibria in Competitive Neural Networks With Discontinuous Nonmonotonic Piecewise Linear Activation Functions
Nie, Xiaobing
Zheng, Wei Xing
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 46 (03) : 679 - 693
[46] Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems
Fudan Univ, Shanghai, China
IEEE Trans Neural Networks, 4 (911-917):
[47] Quantum activation functions for quantum neural networks
Marco Maronese
Claudio Destri
Enrico Prati
Quantum Information Processing, 21
[48] HOLDER CONTINUOUS ACTIVATION FUNCTIONS IN NEURAL NETWORKS
Tatar, Nasser-Eddine
ADVANCES IN DIFFERENTIAL EQUATIONS AND CONTROL PROCESSES, 2015, 15 (02): : 93 - 106
[49] A Comparison of Activation Functions in Artificial Neural Networks
Bircanoglu, Cenk
Arica, Nafiz
2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2018,
[50] Ultra-low-voltage integrable electronic implementation of delayed inertial neural networks for complex dynamical behavior using multiple activation functions
Khanday, Farooq Ahmad
Dar, Mohammad Rafiq
Kant, Nasir Ali
Zulkifli, Tun Zainal Azni
Psychalinos, Costas
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (12): : 8297 - 8314

← 1 2 3 4 5 →