Investigating redundancy in feed-forward neural classifiers

Ž . In this article we will focus on how we can investigate read visualise the clustering behaviour of neurons during training. This clustering property has already been investigated before, by Annema, Vogtlander and Schmidt. However, we ̈ will present a different approach in visualisation illustrated by experiments performed on two-class problems. q 1997 Elsevier Science B.V.