Design strategies for weight matrices of Echo State Networks

Tobias Strauß; Welf Wustlich; Roger Labahn

doi:10.18453/rosdok_id00005823

zum übergeordneten Dokument

Tobias Strauß Welf Wustlich Roger Labahn

Design strategies for weight matrices of Echo State Networks

University of Rostock, Institute of Mathematics, 2012

https://doi.org/10.18453/rosdok_id00005823

Abstract: This article develops approaches to generate dynamical reservoirs of ESNs with desired properties reducing the amount of randomness. It is possible to create weight matrices with a predefined singular value spectrum. The procedure guarantees stability (Echo State property) and minimizes the Impact of noise on the training process. The final reservoir types were already known in the literature but related Input weights were out of the scope of previous articles. But our experiments show, that well chosen input weights can improve performance.

Workingpaper Freier Zugang

Titel:

Design strategies for weight matrices of Echo State Networks

Schriftenreihe:

Preprints aus dem Institut für Mathematik, 12/1

Beteiligte Personen:

Tobias Strauß[VerfasserIn]
	0000-0002-5344-4188
	1136294554
Welf Wustlich[VerfasserIn]
Roger Labahn[VerfasserIn]
	0000-0003-1901-9644
	170999645

Zusammenfassung:

This article develops approaches to generate dynamical reservoirs of ESNs with desired properties reducing the amount of randomness. It is possible to create weight matrices with a predefined singular value spectrum. The procedure guarantees stability (Echo State property) and minimizes the Impact of noise on the training process. The final reservoir types were already known in the literature but related Input weights were out of the scope of previous articles. But our experiments show, that well chosen input weights can improve performance. [Englisch]

Dokumenttyp:

Workingpaper

Einrichtung:

Mathematisch-Naturwissenschaftliche Fakultät

Sprache:

Englisch

Sachgruppe der DNB:

510 Mathematik

Umfang:

1 Online-Ressource (29 Seiten)

Veröffentlichung /
Entstehung:

Rostock: University of Rostock, Institute of Mathematics