title: Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks
creator: Vamplew, P
creator: Adams, A
subject: 280200 Artificial Intelligence and Signal and Image Processing
description: 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.
date: 1994
type: Conference or Workshop Item
type: PeerReviewed
format: application/pdf
identifier: http://eprints.utas.edu.au/41/1/transplant-acnn94.pdf
identifier: Vamplew, P and Adams, A (1994) Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks. In: Fifth Australian Conference on Neural Networks, February 1994, University of Queensland.
relation: http://eprints.utas.edu.au/41/