Switching analysis of 2-D neural networks with nonsaturating linear threshold transfer functions

Authors:
Hong Qu;Zhang Yi;XiaoBin Wang
Affiliations:
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, People's Republic of China;School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, People's Republic of China;School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, People's Republic of China
Venue:
Neurocomputing
Year:
2008

Citing 9
Cited 2

Delay induced periodicity in a neural netlet of excitation and inhibition

Physica D
On the piecewise analysis of networks of linear threshold neurons

Neural Networks
Stability and bifurcation in a neural network model with two delays

Physica D
Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions

Neural Computation
Analysis of Cyclic Dynamics for Networks of Linear Threshold Neurons

Neural Computation
Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions

Neural Computation
A Competitive-Layer Model for Feature Binding and Sensory Segmentation

Neural Computation
On neurodynamics with limiter function and linsker's developmental model

Neural Computation
Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions

IEEE Transactions on Neural Networks

Convergence analysis of a class of simplified background neural networks with two subnetworks

Neurocomputing
Continuous attractors of a class of neural networks with a large number of neurons

Computers & Mathematics with Applications

Quantified Score

Hi-index	0.01

Visualization

Abstract

Multistable neural networks have attracted much interesting in recent years, since the monostable networks are computationally restricted. Several papers have been proposed to study the dynamical behavior of a class of neural networks with nonsaturating linear threshold transfer functions, in which multiple equilibria can coexist. But much of those methods belong to a static category, which does not consider the behavior arising from the switching of different partitions. This paper focuses on the analysis of the network's behavior when those switching arising from one partition to another dynamically. The contributions of this paper are: (1) Dynamical properties of the equilibria of two-dimensional networks are analyzed theoretically. (2) It proves by mathematics that the given conditions can drive the network (two-dimensional) converging to the different global stable stationary points, or the different multistable stationary points. (3) Digital computer simulations are carried out to validate the performance of our theory findings.