TY  - CONF
ID  - epprod41
UR  - http://eprints.utas.edu.au/41/
A1  - Vamplew, P
A1  - Adams, A
Y1  - 1994///
N2  - 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.
KW  - recurrent neural networks
KW  -  pre-training
KW  -  weight initialisation
TI  - Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks
AV  - public
M2  - University of Queensland
T2  - Fifth Australian Conference on Neural Networks
ER  -