Benchmarking reservoir computing on time-independent classification tasks

Authors:
Luís A. Alexandre;Mark J. Embrechts;Jonathan Linton
Affiliations:
Department of Informatics, Univ. Beira Interior, and the Instituto de Teleccomunicações, Covilhã, Portugal;Decision Sciences and Engineering Systems CII 5219, Rensselaer Polytechnic Institute, Troy, NY;Telfer School of Management, University of Ottawa, Ottawa, Canada
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 1

Least Squares Support Vector Machine Classifiers

Neural Processing Letters
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Pattern Recognition and Neural Networks

Pattern Recognition and Neural Networks
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
Kernel partial least squares regression in reproducing kernel hilbert space

The Journal of Machine Learning Research
2007 Special Issue: An experimental unification of reservoir computing methods

Neural Networks
2007 Special Issue: Learning grammatical structure with Echo State Networks

Neural Networks
Adaptive mixtures of local experts

Neural Computation
Delay learning and polychronization for reservoir computing

Neurocomputing

Reservoir Size, Spectral Radius and Connectivity in Static Classification Problems

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I

Quantified Score

Hi-index	0.00

Visualization

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.