| title: |
| Design strategies for weight matrices of Echo State Networks |
|
| series: |
|
| contributing persons: |
|
| |
| 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.
[English] |
|
| document type: |
|
| institution: |
| Faculty of Mathematics and Natural Sciences |
|
| language: |
|
| subject class (DDC): |
|
| extent: |
|
1 Online-Ressource (29 Seiten)
|
|
| |
publication /
production: |
|
Rostock: University of Rostock, Institute of Mathematics
|
|
2012
|
|
| statement of responsibility: |
| Tobias Strauß, Welf Wustlich, Roger Labahn |
|
| |
| identifiers: |
|
| |
| access condition: |
|
| license/rights statement: |
all rights reserved
This work may only be used under the terms of the German Copyright Law (Urheberrechtsgesetz). |
|
|
| RosDok id: |
rosdok_document_0000027958 |
| created / modified: |
13.10.2026 / 13.10.2026
|
| metadata license: |
The metadata of this document was dedicated to the public domain
(CC0 1.0 Universal Public Domain Dedication). |
access
viewer
fulltext