Abstract:
|
This work presents a class of functions serving
as generalized neuron models to be used in artificial neural
networks. They are cast in the common framework of computing a {it
similarity} function, a flexible definition of a neuron as a
pattern recognizer. The similarity endows the model with a clear
conceptual view and serves as a unification cover for many of the
existing neural models, including those classically used for the
MultiLayer Perceptron (MLP) and most of those used in Radial Basis
Function Neural Networks (RBF). The possibilities of deriving new
instances are then explored and several neuron models
--representative of their families-- are proposed. These families of
models are conceptually unified and their relation is clarified.
In addition, the similarity view leads naturally to
further extensions of the models to handle heterogeneous
information, that is to say, information coming from sources
radically different in character, including continuous and discrete
(ordinal) numerical quantities, nominal (categorical) quantities,
and fuzzy quantities. Missing data are also treated explicitly as
such. A neuron of this class is called an {em heterogeneous neuron}
and any neural structure making use of them is an Heterogeneous
Neural Network (HNN), regardless of the specific architecture or
learning algorithm. In this work the experiments are restricted to
feed-forward networks, as the initial focus of study. The learning
procedures may include a great variety of techniques, basically
divided in derivative-based methods (such as the conjugate gradient)
and evolutionary ones (such as genetic algorithms). |