Paper from nEuro'88 in Paris

[Orjan Ekeberg]

The following paper, presented at the nEuro'88 conference in Paris,
has been sent for publication in the proceedings. Reprint requests
can be sent to orjan at bion.kth.se (no cc to connectionists at ... please).

===============

AUTOMATIC GENERATION OF INTERNAL REPRESENTATIONS IN A
PROBABILISTIC ARTIFICIAL NEURAL NETWORK

Orjan Ekeberg, Anders Lansner

Department of Numerical Analysis and Computing Science
The Royal Institute of Technology, S-100 44 Stockholm, Sweden

ABSTRACT

In a one layer feedback perceptron type network, the connections can be
viewed as coding the pairwise correlations between activity in the
corresponding units. This can then be used to make statistical inference
by means of a relaxation technique based on bayesian inferences.

When such a network fails, it might be because the regularities are not
visible as pairwise correlations. One cure would then be to use a different
internal coding where selected higher order correlations are explicitly
represented. A method for generating this representation automatically is
presented with a special focus on the networks ability to generalize properly.