Loading...
conference paper
Reservoir Optimization in Recurrent Neural Networks using Kronecker Kernels
2008
IEEE ISCAS 2008
In this paper, using the mathematical properties of self-kronecker-production of small size random matrices, a simple but effective method is presented to optimize the reservoir of an echo state network given a certain task. The experimental results investigating the NARMA system show that few steps of the proposed optimization process can lead to a near optimum solution.
Type
conference paper
Web of Science ID
WOS:000258532100221
Authors
Publication date
2008
Publisher
Published in
IEEE ISCAS 2008
Start page
868
End page
871
Peer reviewed
REVIEWED
EPFL units
Event name | Event place | Event date |
Seattle, WA | May 18-21, 2008 | |
Available on Infoscience
June 16, 2008
Use this identifier to reference this record