Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!ames!ucsd!sdcsvax!beowulf!biafore
From: biafore@beowulf.ucsd.edu (Louis Steven Biafore)
Newsgroups: comp.ai.neural-nets
Subject: Tech report available
Keywords: backpropagation, dynamic node creation
Message-ID: <6072@sdcsvax.UCSD.Edu>
Date: 7 Mar 89 20:43:19 GMT
Sender: nobody@sdcsvax.UCSD.Edu
Reply-To: biafore%cs.UCSD.EDU
Distribution: na
Organization: Computer Science & Engineering Dept. U.C. San Diego
Lines: 46


-----------------------------------------------------------------------
The following technical report is now available.  
-----------------------------------------------------------------------


                   DYNAMIC NODE CREATION
                             IN
                  BACKPROPAGATION NETWORKS

                         Timur Ash
                        ash@ucsd.edu


                          Abstract


     Large backpropagation (BP) networks are very  difficult
to  train.  This fact complicates the process of iteratively
testing different sized networks (i.e., networks  with  dif-
ferent  numbers of hidden layer units) to find one that pro-
vides a good mapping approximation.  This paper introduces a
new  method  called Dynamic Node Creation (DNC) that attacks
both of these issues (training large  networks  and  testing
networks with different numbers of hidden layer units).  DNC
sequentially adds nodes one at a time to the hidden layer(s)
of  the  network until the desired approximation accuracy is
achieved.  Simulation results for parity,  symmetry,  binary
addition,  and  the encoder problem are presented.  The pro-
cedure was capable of finding known  minimal  topologies  in
many  cases,  and  was  always  within  three  nodes  of the
minimum. Computational expense for finding the solutions was
comparable  to  training  normal  BP  networks with the same
final topologies.  Starting out with fewer nodes than needed
to solve the problem actually seems to help find a solution.
The method yielded a solution for every problem  tried.   BP
applied  to  the same large networks with randomized initial
weights was unable, after repeated  attempts,  to  replicate
some minimum solutions found by DNC.

-----------------------------------------------------------------------
Requests for reprints should be sent to the Institute for Cognitive 
Science, C-015; University of California, San Diego; La Jolla, CA 92093.

(ICS Report 8901)
-----------------------------------------------------------------------