NeuroCOLT: Neural Networks and Computational Learning Theory

NeuroCOLT

Neural Networks and Computational Learning Theory

1994	1995
1996	1997
1998	1999
2000	2001

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-97-014

A New Incremental Learning Technique

Nick Dunkin, John Shawe-Taylor
Royal Holloway, University of London, UK

Pascal Koiran
LIP ENS Lyon, France

Abstract
We present a new type of constructive algorithm for incremental learning. The algorithm overcomes many of the problems associated with standard back propagation such as speed and optimum network size. We investigate the ability of the network to learn and test the resulting generalisation of the network.

Download Compressed Postscript