Library Open Repository

Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks

Downloads

Downloads per month over past year

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.

[img]
Preview
PDF
transplant-acnn94.pdf | Download (149kB)
Available under University of Tasmania Standard License.

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.

Item Type: Conference or Workshop Item (Paper)
Keywords: recurrent neural networks, pre-training, weight initialisation
Date Deposited: 12 Aug 2004
Last Modified: 18 Nov 2014 03:10
URI: http://eprints.utas.edu.au/id/eprint/41
Item Statistics: View statistics for this item

Repository Staff Only (login required)

Item Control Page Item Control Page