DocumentCode
2712026
Title
Benchmarking reservoir computing on time-independent classification tasks
Author
Alexandre, Luís A. ; Embrechts, Mark J. ; Linton, Jonathan
Author_Institution
Dept. of Inf., Univ. Beira Interior, Covilha, Portugal
fYear
2009
fDate
14-19 June 2009
Firstpage
89
Lastpage
93
Abstract
This paper presents an extensive evaluation of reservoir computing for the case of classification problems that do not depend on time.We discuss how it is possible to adapt the reservoir approach to learning for the case of static classification problems. Then we present a set of experiments against K-PLS, MLP with entropic cost function and LS-SVM showing that this approach is quite competitive and has the advantage of having only one parameter to be chosen.
Keywords
pattern classification; K-PLS; LS-SVM; MLP; entropic cost function; reservoir approach; reservoir computing; static classification problem; time-independent classification task; Computer networks; Cost function; Least squares methods; Machine learning; Neural networks; Recurrent neural networks; Reservoirs; Robot control; Speech recognition; Transfer functions;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location
Atlanta, GA
ISSN
1098-7576
Print_ISBN
978-1-4244-3548-7
Electronic_ISBN
1098-7576
Type
conf
DOI
10.1109/IJCNN.2009.5178920
Filename
5178920
Link To Document