%0 Conference Paper
%9 Unspecified
%A Vamplew, P
%A Adams, A
%B Fifth Australian Conference on Neural Networks
%C University of Queensland
%D 1994
%F epprod:41
%K recurrent neural networks, pre-training, weight initialisation
%T Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks
%U http://eprints.utas.edu.au/41/
%X Partially-recurrent networks have advantages over strictly feed-forward networks for certain spatiotemporal pattern classification or prediction tasks. However networks involving recurrent links are generally more difficult to train than their non-recurrent counterparts. In this paper we demonstrate that the costs of training a recurrent network can be greatly reduced by initialising the network prior to training with weights 'transplanted' from a non-recurrent architecture.