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

Authors:
Fang Xu;Zhang Yi
Affiliations:
School of Sciences, Southwest Petroleum University, Chengdu 610500, PR China;Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu 610065, PR China
Venue:
Neurocomputing
Year:
2011

Citing 9
Cited 0

On numerical simulations of integrate-and-fire neural networks

Neural Computation
On the piecewise analysis of networks of linear threshold neurons

Neural Networks
Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions

Neural Computation
Background synaptic activity as a switch between dynamical states in a network

Neural Computation
Annealed competition of experts for a segmentation and classification of switching dynamics

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

Neurocomputing
Some multistability properties of bidirectional associative memory recurrent neural networks with unsaturating piecewise linear transfer functions

Neurocomputing
A recurrent neural network for nonlinear optimization with a continuously differentiable objective function and bound constraints

IEEE Transactions on Neural Networks
Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Motivated by Salinas's (2003) original discovery in [1] and inspired by Oja's (1982) seminal work in [2], in this paper, we propose a class of simplified background neural networks model with two subnetworks. Some basic dynamic properties including boundedness, global attractivity, stability, and complete convergence are analyzed rigorously. The main contributions in this paper are as follows: (1) The boundedness of the new model is verified and conditions for global attractivity are derived. (2) Conditions on asymptotically stable of equilibrium points are obtained. (3) Complete convergence for the new network is proved by constructing a novel energy function. Finally, numerical examples demonstrate our theoretical results.