Echo state networks with sparse output connections

Authors:
Hans-Ulrich Kobialka;Umer Kayani
Affiliations:
Fraunhofer Institut Intelligente Analyse- und Informationssysteme IAIS, Sankt Augustin, Germany;Fraunhofer Institut Intelligente Analyse- und Informationssysteme IAIS, Sankt Augustin, Germany
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part I
Year:
2010

Citing 8
Cited 0

Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
An introduction to variable and feature selection

The Journal of Machine Learning Research
Editorial: Special issue on echo state networks and liquid state machines

Neural Networks
Markov blanket-embedded genetic algorithm for gene selection

Pattern Recognition
Pruning and regularization in reservoir computing

Neurocomputing
Sparse Coding Neural Gas: Learning of overcomplete data representations

Neurocomputing
Survey: Reservoir computing approaches to recurrent neural network training

Computer Science Review
Support Vector Echo-State Machine for Chaotic Time-Series Prediction

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

An Echo State Network transforms an incoming time series signal into a high-dimensional state space, and, of course, not every dimension may contribute to the solution. We argue that giving low weights via linear regression is not sufficient. Instead irrelevant features should be entirely excluded from directly contributing to the output nodes. We conducted several experiments using two state-of-the-art feature selection algorithms. Results show significant reduction of the generalization error.