Entropy-based Stability of Fractional Self-Organizing Maps with Different Time Scales
Abstract
The behavior of self-organizing neural maps, which develop through a combination of long and short-term memory, involves different time scales. Such a neural network's activity is characterized by a neural activity equation representing the fast phenomenon and a synaptic information efficiency equation representing the slow part of the neural system. The work reported here proposes a new method to analyze the dynamics of self-organizing maps based on the flow-invariance principle, considering the performance of the system's different time scales. In this approach, the equilibrium point is determined based on the estimate for the entropy at each iteration of the learning rule, which is generally sufficient to analyze existence and uniqueness. In this sense, the viewpoint reported here proves the existence and uniqueness of the equilibrium point on a fractional approach by using a Lyapunov method extension for Caputo derivatives when 0 < < 1. Furthermore, the global exponential stability of the equilibrium point is proven with a strict Lyapunov function for the flow of the system with different time scales and some numerical simulations.
Downloads
How to Cite
References
A. Meyer-Baese, S. Pilyugin, Y. Chen (2003) Global exponential stability of competitive neural networks with different time scales. 14(3), 716-719. https://doi.org/10.1109/tnn.2003.810594
S. Amari (1982) Competitive and Cooperative Aspects in Dynamics of Neural Excitation and Self-Organization. 1982, 1-28. https://doi.org/10.1007/978-3-642-46466-91
Michael Lemmon, B. Vijaya Kumar (1989) Emulating the dynamics for a class of laterally inhibited neural networks, Neural Networks 2 (3) (1989). 2(3), 193-214. https://doi.org/10.1016/0893-6080(89)90004-x
Michael London, Adi Schreibman, Michael Häusser, Matthew Larkum, Idan Segev (2002) The information efficacy of a synapse. 5(4), 332-340. https://doi.org/10.1038/nn826
How patterned neural connections can be set up by self-organization (1976) Proceedings of the Royal Society of London. Series B. Biological Sciences. 194(1117), 431-445. https://doi.org/10.1098/rspb.1976.0087
Sohrab Najafian, Erin Koch, Kai Teh, Jianzhong Jin, Hamed Rahimi-Nasrabadi, Qasim Zaidi, Jens Kremkow, Jose-Manuel Alonso (2022) A theory of cortical map formation in the visual brain, Nature Communications 13 (1) (Apr. 13(1). https://doi.org/10.1038/s41467-022-29433-y
Norelys Aguila-Camacho, Manuel Duarte-Mermoud, Javier Gallegos (2014) Lyapunov functions for fractional order systems. 19(9), 2951-2957. https://doi.org/10.1016/j.cnsns.2014.01.022
Shuo Zhang, Yongguang Yu, Junzhi Yu (2017) LMI Conditions for Global Stability of Fractional-Order Neural Networks. 28(10), 2423-2433. https://doi.org/10.1109/tnnls.2016.2574842
Jia Jia, Xia Huang, Yuxia Li, Jinde Cao, Ahmed Alsaedi (2020) Global Stabilization of Fractional-Order Memristor-Based Neural Networks With Time Delay. 31(3), 997-1009. https://doi.org/10.1109/tnnls.2019.2915353
Ailong Wu, Zhigang Zeng (2017) Global Mittag-Leffler Stabilization of Fractional-Order Memristive Neural Networks. 28(1), 206-217. https://doi.org/10.1109/tnnls.2015.2506738
Jiejie Chen, Zhigang Zeng, Ping Jiang (2014) Global Mittag-Leffler stability and synchronization of memristor-based fractional-order neural networks. 51, 1-8. https://doi.org/10.1016/j.neunet.2013.11.016
Thomas Cover, Joy Thomas (2006) Elements of Information Theory. https://doi.org/10.1002/0471200611
G. Saridis (2001) Entropy In Control Engineering.
C. Peña Fern´ández (2023) ´ández, An ergodic selection method for kinematic configurations in autonomous, flexible mobile systems. 109(1). https://doi.org/10.1007/s10846-023-01933-z
Chao He, Ming Li, Congxuan Zhang, Hao Chen, Peilong Zhong, Zhengxiu Li, Junhua Li (2022) A self-organizing map approach for constrained multi-objective optimization problems. 8(6), 5355-5375. https://doi.org/10.1007/s40747-022-00761-2
Published
2024-02-23
Issue
Section
License
Copyright (c) 2024 Authors and Global Journals Private Limited

This work is licensed under a Creative Commons Attribution 4.0 International License.