Neural Transplant Surgery: An Approach to Pre-training Recurrent Networks
暂无分享,去创建一个
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.
[1] P J Webros. BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .
[2] Geoffrey E. Hinton,et al. A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.
[3] Ronald J. Williams,et al. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.
[4] Geoffrey E. Hinton,et al. Proceedings of the 1988 Connectionist Models Summer School , 1989 .