U. Helmke et Rc. Williamson, NEURAL NETWORKS, RATIONAL FUNCTIONS, AND REALIZATION-THEORY, MCSS. Mathematics of control, signals and systems, 8(1), 1995, pp. 27-49
Citations number
26
Categorie Soggetti
Controlo Theory & Cybernetics","Engineering, Eletrical & Electronic",Mathematics,"Robotics & Automatic Control
The problem of parametrizing single hidden layer scalar neural network
s with continuous activation functions is investigated. A connection i
s drawn between realization theory for linear dynamical systems, ratio
nal functions, and neural networks that appears to be new. A result of
this connection is a general parametrization of such neural networks
in terms of strictly proper rational functions. Some existence and uni
queness results are derived. Jordan decompositions are developed, whic
h show how the general form can be expressed in terms of a sum of cano
nical second order sections. The parametrization may be useful for stu
dying learning algorithms.