Journal
NEUROCOMPUTING
Volume 72, Issue 7-9, Pages 1534-1546Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2008.12.020
Keywords
Reservoir computing; Echo state network; Variable selection; Regularization; Ridge regression
Categories
Ask authors/readers for more resources
Reservoir computing is a new paradigm for using recurrent neural network with a much simpler training method. The key idea is to use a large but fixed recurrent part as a reservoir of dynamic features and to train only the output layer to extract the desired information. We propose to study how pruning some connections from the reservoir to the output layer can help on the one hand to increase the generalization ability, in much the same way as regularization techniques do, and on the other hand to improve the implementability of reservoirs in hardware. (C) 2009 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available