ON THE USE OF A PRUNING PRIOR FOR NEURAL NETWORKS
          =================================================

                           C. Goutte

           Department of Mathematical Modeling - Bygn. 349
           Technical University of Denmark
           DK-2800 Lyngby, Denmark
           Phone: +45 4525 5738
           Fax: +45 4288 0117
           E-mail: goutte@ei.dtu.dk, goutte@laforia.ibp.fr


We adress the problem of using a regularization prior that prunes
unnecessary weights in a neural network architecture.  This prior
provides a convenient alternative to traditional
\textit{weight-decay}.  Two examples are studied to support this
method and illustrate its use.  First we use the sunspots benchmark
problem as an example of time series processing.  Then we adress the
problem of system identification on a small artificial system.