Neural Computation, Vol 9, 161-183, Copyright © 1997 by The MIT Press
Selecting Optimal Experiments for Multiple Output Multilayer Perceptrons
Lisa M. Belue, Kenneth W. Bauer Jr. and Dennis W. Ruck
Where should a researcher conduct experiments to provide training data for
a multilayer perceptron? This question is investigated, and a statistical
method for selecting optimal experimental design points for multiple output
multilayer perceptrons is introduced. Multiple class discrimination
problems are examined using a framework in which the multilayer perceptron
is viewed as a multivariate nonlinear regression model. Following a
Bayesian formulation for the case where the variance-covariance matrix of
the responses is unknown, a selection criterion is developed. This
criterion is based on the volume of the joint confidence ellipsoid for the
weights in a multilayer perceptron. An example is used to demonstrate the
superiority of optimally selected design points over randomly chosen
points, as well as points chosen in a grid pattern. Simplification of the
basic criterion is offered through the use of Hadamard matrices to produce
uncorrelated outputs.
