paper available: learning in a committee machine

[Robert Urbanczik]

FTP-host:       ftp.physik.uni-wuerzburg.de
FTP-filename:   /pub/preprint/WUE-ITP-96-013.ps.gz
**DO NOT FORWARD TO OTHER GROUPS**



The following paper (9 pages, to appear in Europhys.Letts.)
is now available via anonymous ftp:
(See below for the retrieval procedure)

---------------------------------------------------------------------
Learning in a large committee machine:
Worst case and average case

by R. Urbanczik

Abstract:
  Learning of realizable rules is studied for tree committee machines
  with continuous weights. No nontrivial upper bound exists for
  the generalization error of consistent students as the number of hidden
  units $K$ increases. However, numerical considerations show that
  consistent students with
  a value of the generalization error significantly higher than predicted
  by the average case analysis are extremely hard to find. An on-line
  learning algorithm is presented, for which the generalization error scales
  with the training set size as in the average case theory in the limit
  of large $K$.

---------------------------------------------------------------------

Retrieval procedure:

     unix> ftp  ftp.physik.uni-wuerzburg.de
     Name: anonymous  Password: {your e-mail address}
     ftp>  cd pub/preprint/1996
     ftp>  get WUE-ITP-96-013.ps.gz
     ftp>  quit
     unix> gunzip WUE-ITP-96-013.ps.gz
e.g. unix> lp WUE-ITP-96-013.ps

_____________________________________________________________________