41 4 archive 4 disk0/00/00/00/41 2004-08-12 2008-07-18 09:37:08 2008-07-16 15:40:19 conference_item show Vamplew P Adams A pub 280200 public NULL paper recurrent neural networks, pre-training, weight initialisation 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. 1994 published Fifth Australian Conference on Neural Networks University of Queensland February 1994 conference TRUE 322 1 41 1 application/pdf en public cc_utas

transplant-acnn94.pdf

transplant-acnn94.pdf 149855 http://eprints.utas.edu.au/41/1/transplant-acnn94.pdf