INVESTIGATING REDUNDANCY IN FEEDFORWARD NEURAL CLASSIFIERS

in this article we will focus on how we can investigate (read visualis e) the clustering behaviour of neurons during training. This clusterin g properly has already been investigated before, by Annema, Vogtlander and Schmidt. However, we will present a different approach in visuali sation illustrated by experiments performed on two-class problems. (C) 1997 Elsevier Science B.V.