%0 Book %T Design strategies for weight matrices of Echo State Networks %A Strauß, Tobias %A Wustlich, Welf %A Labahn, Roger %S Preprints aus dem Institut für Mathematik %D 2012 %C Germany; Rostock %G English %F 1986677001 %O Tobias Strauß, Welf Wustlich, Roger Labahn %X 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. %L 510 %9 Text %R 10.18453/rosdok_id00005823 %U https://purl.uni-rostock.de/rosdok/id00005823 %U https://doi.org/10.18453/rosdok_id00005823