Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks
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.
|PDF - Requires a PDF viewer|
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|
|Deposited By:||utas eprints|
|Deposited On:||12 Aug 2004|
|Last Modified:||18 Jul 2008 19:37|
|ePrint Statistics:||View statistics for this ePrint|
Repository Staff Only: item control page