1736 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS—I: REGULAR PAPERS, VOL. 54, NO. 8, AUGUST 2007
Dynamical Analysis of Full-Range Cellular
Neural Networks by Exploiting Differential
Variational Inequalities
Guido De Sandre, Mauro Forti, Paolo Nistri, and Amedeo Premoli
Abstract—The paper considers the full-range (FR) model of
cellular neural networks (CNNs) in the case where the neuron
nonlinearities are ideal hard-comparator functions with two
vertical straight segments. The dynamics of FR-CNNs, which is
described by a differential inclusion, is rigorously analyzed by
means of theoretical tools from set-valued analysis and differential
inclusions. The fundamental property proved in the paper is that
FR-CNNs are equivalent to a special class of differential inclusions
termed differential variational inequalities. A sound foundation
to the dynamics of FR-CNNs is then given by establishing the
existence and uniqueness of the solution starting at a given point,
and the existence of equilibrium points. Moreover, a fundamental
result on trajectory convergence towards equilibrium points
(complete stability) for reciprocal standard CNNs is extended to
reciprocal FR-CNNs by using a generalized Lyapunov approach.
As a consequence, it is shown that the study of the ideal case with
vertical straight segments in the neuron nonlinearities is able to
give a clear picture and analytic characterization of the salient
features of motion, such as the sliding modes along the boundary
of the hypercube defined by the hard-comparator nonlinearities.
Finally, it is proved that the solutions of the ideal FR model are
the uniform limit as the slope tends to infinity of the solutions
of a model where the vertical segments in the nonlinearities are
approximated by segments with finite slope.
Index Terms—Cellular neural networks (CNNs), differential in-
clusions, full-range (FR) model, sliding modes, trajectory conver-
gence, variational inequalities.
NOTATION
Real -space.
, Square matrix.
Transpose of .
Inverse of .
, Column
vector.
Manuscript received September 25, 2004; revised November 29, 2006 and
January 14, 2007. This paper was recommended by Associate Editor L. Tra-
jkovic.
G. De Sandre is with STMicroelectronics, 20041 Agrate Brianza, Italy
(e-mail: guido.de-sandre@st.com).
M. Forti and P. Nistri are with the Dipartimento di Ingegneria dell’Infor-
mazione, Università di Siena, 53100 Siena, Italy (e-mail: forti@dii.unisi.it;
pnistri@dii.unisi.it).
A. Premoli is with the Dipartimento di Elettronica e Informazione, Politec-
nico di Milano, 20133 Milan, Italy.
Digital Object Identifier 10.1109/TCSI.2007.902607
, Scalar product of
.
, Euclidean norm
of .
,
-dimensional open ball with center
0 and radius .
Closure of set .
Interior of .
Boundary of .
, Distance of
from .
Tangent cone to at .
Normal cone to at .
Projector of best approximation of
on .
Difference of sets .
Element of with the smallest
norm.
Linear subspace of spanned by
vectors .
Direct sum of subspaces and .
Empty set.
(Conventional) single-valued
function.
(Conventional) gradient of .
Extended-valued function.
Graph of .
Epigraph of .
Generalized gradient of .
I. INTRODUCTION
T
HE standard (S) cellular neural networks (S-CNNs) intro-
duced by Chua and Yang [1] have been one of the most
investigated neural paradigms for real time signal processing.
1549-8328/$25.00 © 2007 IEEE