Title
Limit Set Dichotomy and Convergence of Cooperative Piecewise Linear Neural Networks.
Abstract
This paper considers a class of nonsymmetric cooperative neural networks (NNs) where the neurons are fully interconnected and the neuron activations are modeled by piecewise linear (PL) functions. The solution semiflow generated by cooperative PLNNs is monotone but, due to the horizontal segments in the neuron activations, is not eventually strongly monotone (ESM). The main result in this paper is that it is possible to prove a peculiar form of the LIMIT SET DICHOTOMY for this class of cooperative PLNNs. Such a form is slightly weaker than the standard form valid for ESM semiflows, but this notwithstanding it permits to establish a result on convergence analogous to that valid for ESM semiflows. Namely, for almost every choice of the initial conditions, each solution of a fully interconnected cooperative PLNN converges toward an equilibrium point, depending on the initial conditions, as t -> +infinity From a methodological viewpoint, this paper extends some basic techniques and tools valid for ESM semiflows, in order that they can be applied to the monotone semiflows generated by the considered class of cooperative PLNNs.
Year
DOI
Venue
2011
10.1109/TCSI.2010.2091194
IEEE Trans. on Circuits and Systems
Keywords
Field
DocType
integrated circuit interconnections,neural chips,piecewise linear techniques,set theory,ESM semiflow,cooperative piecewise linear neural network,equilibrium point,fully interconnected cooperative PLNN,limit set dichotomy,monotone semiflow,neuron activation,nonsymmetric cooperative neural network,piecewise linear function,Convergence,cooperative neural networks,dynamical systems,limit set dichotomy,monotone and eventually strongly monotone semiflows
Convergence (routing),Set theory,Control theory,Equilibrium point,Strongly monotone,Dynamical systems theory,Piecewise linear function,Mathematics,Monotone polygon,Limit set
Journal
Volume
Issue
ISSN
58-I
5
1549-8328
Citations 
PageRank 
References 
14
0.78
11
Authors
4
Name
Order
Citations
PageRank
Mauro Di Marco120518.38
Mauro Forti239836.80
Massimo Grazzini313111.01
Luca Pancioni420717.58