Journal
NONLINEAR ANALYSIS-REAL WORLD APPLICATIONS
Volume 45, Issue -, Pages 799-821Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.nonrwa.2018.08.005
Keywords
Competitive neural networks; Multistability; Instability; Non-monotonic piecewise linear activation functions
Categories
Funding
- National Natural Science Foundation of China [61673111, 61833005, 61573096]
- 333 Engineering Foundation of Jiangsu Province of China [BRA2015286]
- Qing Lan Project of Jiangsu Province of China
- Jiangsu Provincial Key Laboratory of Networked Collective Intelligence [BM2017002]
Ask authors/readers for more resources
This paper addresses the issue of multistability for competitive neural networks. First, a general class of continuous non-monotonic piecewise linear activation functions is introduced. Then, based on the fixed point theorem, the contraction mapping theorem and the eigenvalue properties of strict diagonal dominance matrix, it is shown that under some conditions, such n-neuron competitive neural networks have exactly 5(n) equilibrium points, among which 3(n) equilibrium points are locally exponentially stable and the others are unstable. Moreover, it is revealed that the neural networks with non-monotonic piecewise linear activation functions introduced in this paper can have greater storage capacity than the ones with Mexican-hat-type activation function and nondecreasing saturated activation function. In addition, unlike most existing multistability results of neural networks with nondecreasing activation functions, the location of those obtained 3(n) locally stable equilibrium points in this paper is more flexible. Finally, a numerical example is provided to illustrate and validate the theoretical findings via comprehensive computer simulations. (C) 2018 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available