Golden, R. M. (1988).
A unified framework for connectionist systems,
Biological Cybernetics, 59,
109-120.
ABSTRACT (Note: My recent book presents
my current related thoughts on the theory sketched here)
Pattern classification using connectionist (i.e., neural network)
models is viewed within a statistical framework.
A connectionist network's subjective beliefs about its statistical
environment are derived. This belief structure is the network's
"subjective" probability distribution. Stimulus classification is
interpreted as computing the "most probable" response for a given
stimulus with respect to the subjective probability distribution.
Given the subjective probability distribution, learning algorithms
can be analyzed and designed using maximum likelihood estimation
techniques, and statistical tests can be developed to evaluate
and compare network architectures. The framework is applicable
to many connectionist networks including those of
Hopfield (1982, 1984), Cohen and Grossberg (1983), Anderson et al. (1977),
and Rumelhart et al. (1986).
Semi-final post script draft
(possibly missing figures)
Golden's Neural Network Publications List