INVESTIGADORES
JULIAN Pedro Marcelo
artículos
Título:
A Piecewise-Linear Simplicial Coupling Cell for CNN Gray-Level Image Processing
Autor/es:
P. JULIÁN, R. DOGARU, L. O. CHUA
Revista:
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS
Editorial:
IEEE
Referencias:
Lugar: NY; Año: 2002 vol. 49 p. 904 - 913
ISSN:
1057-7122
Resumen:
In this paper, we propose a universal piecewise-linear
(PWL) CNN coupling cell, the simplicial cell, which is intended to
work with binary as well as gray-level inputs. The construction of
the cell is based on the theory of canonical simplicial PWL representations.
As a consequence, the coupling function is endowed
with important numerical features, namely: the representation of
the characteristic cell function is sparse; the familiy of coupling
functions constitutes a Hilbert space; powerful solution algorithms
have been developed for the approximation of nonlinear functions,
which is particularly useful when the CNN parameters need to
be tuned from examples; the parameters can be extracted from a
truth table when the CNN is specified analytically.