creators_name: Vamplew, P
creators_name: Adams, A
type: conference_item
datestamp: 2004-08-12
lastmod: 2008-07-18 09:37:08
metadata_visibility: show
title: Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks
ispublished: pub
subjects: 280200
full_text_status: public
monograph_type: NULL
pres_type: paper
keywords: recurrent neural networks, pre-training, weight initialisation
abstract: 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
date_type: published
event_title: Fifth Australian Conference on Neural Networks
event_location: University of Queensland
event_dates: February 1994
event_type: conference
refereed: TRUE
citation: 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.
document_url: http://eprints.utas.edu.au/41/1/transplant-acnn94.pdf