Paper announcements

[Bruce]

                   *** Paper Announcements ***
 
The following paper is now available from my research page:
http://www.cs.utsa.edu/faculty/rosen/rosen.html
 
Comments are welcomed.
 
  -----------------------------------------------------------------------
 
     Ensemble Learning using Decorrelated Neural Networks

                   Bruce E. Rosen
             ftp://ringer.cs.utsa.edu/pub/rosen/decorrelate.ps.Z

We describe a decorrelation network training method for improving the
quality of regression learning in ``ensemble'' neural networks that
are composed of linear combinations of individual neural networks.
In this method, individual networks are trained by backpropagation to
not only reproduce a desired output, but also to have their errors
be linearly decorrelated with the other networks.  Outputs from the
individual networks are then linearly combined to produce the output of
the ensemble network.
 
We demonstrate the performances of decorrelated network training on
learning the ``3 Parity'' logic function, a noisy sine function, and
a one dimensional nonlinear function, and compare the results with the
ensemble networks composed of independently trained individual networks
(without decorrelation training).  Empirical results show that when
individual networks are forced to be decorrelated with one another the
resulting ensemble neural networks have lower mean squared errors than
the ensemble networks having independently trained individual networks.
This method is particularly applicable when there is insufficient data
to train each individual network on disjoint subsets of training patterns.

To appear in: Connection Science, Special issue on Combining Estimators.