transplant-acnn94.pdf (146.34 kB)
Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks
conference contribution
posted on 2023-05-26, 09:55 authored by Vamplew, P, Adams, APartially-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.
History
Publication status
- Published
Event title
Fifth Australian Conference on Neural NetworksEvent Venue
University of QueenslandDate of Event (Start Date)
1994-02-01Date of Event (End Date)
1994-02-01Repository Status
- Open
Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC