|
On the generalization error of fixed combinations of classifiers
Martin Anthony
Journal of Computer and System Sciences
Volume to appear,
2006.
AbstractWe consider the generalization error of concept learning
when using a fixed Boolean function of the outputs of a number of
different classifiers. Here, we take into account the `margins' of
each of the constituent classifiers. A special case is that in
which the constituent classifiers are linear threshold functions
(or perceptrons) and the fixed Boolean function is the majority
function. This corresponds to a `committee of perceptrons', an
artificial neural network (or circuit) consisting of a single
layer of perceptrons (or linear threshold units) in which the
output of the network is defined to be the majority output of the
perceptrons. Recent work of Auer {\em et al.} studied the
computational properties of such networks (where they were called
`parallel perceptrons'), proposed an incremental learning
algorithm for them, and demonstrated empirically that the learning
rule is effective.
As a corollary of the results presented here,
generalization error bounds are derived for this special case that
provide further motivation for the use of this
learning rule. [Edit]
|
