mycoreobjectrosdok_document_0000027958rosdok_document_0000027958rosdokdocumentrosdok_derivate_00002298842026-10-13T13:19:56.901Z2026-10-13T11:59:22.498ZeditorKEeditorKEpublished1rosdok_derivate_0000229884truetruederivate_types:fulltextVolltextfulltextwf_edit_epub wf_register_epubstate:publishedstate:publishedveröffentlichtpublishedrosdok_id000058231986677001Oau2026-10-132026-10-13T13:19:55ZrdaConverted from PICA to MODS using Pica2MODS XSLT Transformer 2.14-SNAPSHOT [SCM: "" "" ""] with mode 'DEFAULT'.WorkingpaperDesign strategies for weight matrices of Echo State NetworksThis 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.TobiasStrauß1984 -VerfasserInaut11362945540000-0002-5344-4188WelfWustlichVerfasserInautRogerLabahn1959 -VerfasserInaut1709996450000-0003-1901-9644https://purl.uni-rostock.de/rosdok/id00005823urn:nbn:de:gbv:28-rosdok_id00005823-510.18453/rosdok_id00005823510 MathematikMathematisch-Naturwissenschaftliche Fakultätalle Rechte vorbehaltenRechteinhaber Universität Rostockfrei zugänglich (Open Access)Lizenz Metadaten: CC0en1 Online-Ressource (29 Seiten)2012University of Rostock, Institute of MathematicsRostockmonographic20122026Universitätsbibliothek RostockRostock2026Universitätsbibliothek Rostockhttps://purl.uni-rostock.de/rosdok/id00005823Tobias Strauß, Welf Wustlich, Roger Labahnrosdok_id000058161986139832Odvhttps://purl.uni-rostock.de/rosdok/id00005816Preprints aus dem Institut für Mathematik3255797-812/10012-0001doctype:epubdoctype:epubDokumenttypDocument typedoctype:epub.workingpaperdoctype:epub.workingpaperWorkingpaperworking paperdiniPublType:workingPaper diniPublType2022:WorkingPaperinfo:eu-repo/semantics/workingPaperdocumentdiniPublType2022:WorkingPaperdiniPublType2022:WorkingPaperArbeitspapierWorking paperKDSF (Pu37)SDNB:510SDNB:510510 Mathematik510 Mathematicsinstitution:unirostockinstitution:unirostockUniversität RostockUniversity of RostockUniversität RostockUniversität RostockUni.Rostockhttp://d-nb.info/gnd/38329-6institution:unirostock.mnfinstitution:unirostock.mnfMathematisch-Naturwissenschaftliche FakultätFaculty of Mathematics and Natural SciencesUniversität Rostock. Mathematisch-Naturwissenschaftliche FakultätMathematisch-Natur-<br />wissenschaftliche FakultätUni.Rostock.Fakultaet.MNFhttp://d-nb.info/gnd/2147083-2licenseinfo:worklicenseinfo:workWerkworklicenseinfo:work.rightsreservedlicenseinfo:work.rightsreservedalle Rechte vorbehaltenall rights reserved/creativecommons/r/reserved/0.9/88x31.png[DE-28]Urheberrechtsschutz 1.0$gRights Statements$uhttp://rightsstatements.org/vocab/InC/1.0/http://rightsstatements.org/vocab/InC/1.0/http://rightsstatements.org/vocab/InC/1.0/licenseinfo:depositlicenseinfo:depositVeröffentlichungsgenehmigungpermission to storelicenseinfo:deposit.rightsunirostocklicenseinfo:deposit.rightsunirostockRechteinhaber Universität Rostockrightsholder Rostock Universityaccesscondition:openaccessaccesscondition:openaccessfrei zugänglich (Open Access)open accesshttp://purl.org/coar/access_right/c_abf2OAfreeinfo:eu-repo/semantics/openAccess[DE-28]Open Access$gControlled Vocabulary for Access Rights$uhttp://purl.org/coar/access_right/c_abf2licenseinfo:metadatalicenseinfo:metadataLizenzen für Metadatenlicenseinfo:metadata.cc0licenseinfo:metadata.cc0Lizenz Metadaten: CC0license metadata: CC0/creativecommons/p/zero/1.0/88x31.pnghttps://creativecommons.org/publicdomain/zero/1.0/rfc5646:enrfc5646:enEnglischEnglishengengDesign strategies for weight matrices of Echo State NetworksDesign strategies for weight matrices of Echo State Networksgnd:1136294554orcid:0000-0002-5344-4188gnd:170999645orcid:0000-0003-1901-9644gnd:1136294554orcid:0000-0002-5344-4188gnd:170999645orcid:0000-0003-1901-9644rosdok_document_0000027958-d4017101e49gnd:1136294554orcid:0000-0002-5344-4188Tobias StraußTobias Straußrosdok_document_0000027958-d4017101e65Welf WustlichWelf Wustlichrosdok_document_0000027958-d4017101e75gnd:170999645orcid:0000-0003-1901-9644Roger LabahnRoger LabahnTobias StraußWelf WustlichRoger LabahnTobias StraußWelf WustlichRoger LabahnTobias StraußWelf WustlichRoger LabahnRostockUniversity of Rostock, Institute of Mathematicsepub.workingpaperhttps://purl.uni-rostock.de/rosdok/id00005823urn:nbn:de:gbv:28-rosdok_id00005823-510.18453/rosdok_id00005823This 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.20122012Preprints aus dem Institut für Mathematikrosdok_id000058161986139832Odvhttps://purl.uni-rostock.de/rosdok/id00005816Preprints aus dem Institut für Mathematik3255797-812/10012-0001https://purl.uni-rostock.de/rosdok/id000058163255797-8Tobias Strauß, Welf Wustlich, Roger Labahnepub.workingpaper1 Strauss_design_2012.pdf 658335 90157e952a797a59295560d1aba3ffec rosdok_id000058231986677001Oau2026-10-132026-10-13T13:19:55ZrdaConverted from PICA to MODS using Pica2MODS XSLT Transformer 2.14-SNAPSHOT [SCM: "" "" ""] with mode 'DEFAULT'.WorkingpaperDesign strategies for weight matrices of Echo State NetworksThis 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.TobiasStrauß1984 -VerfasserInaut11362945540000-0002-5344-4188WelfWustlichVerfasserInautRogerLabahn1959 -VerfasserInaut1709996450000-0003-1901-9644https://purl.uni-rostock.de/rosdok/id00005823urn:nbn:de:gbv:28-rosdok_id00005823-510.18453/rosdok_id00005823510 MathematikMathematisch-Naturwissenschaftliche Fakultätalle Rechte vorbehaltenRechteinhaber Universität Rostockfrei zugänglich (Open Access)Lizenz Metadaten: CC0en1 Online-Ressource (29 Seiten)2012University of Rostock, Institute of MathematicsRostockmonographic20122026Universitätsbibliothek RostockRostock2026Universitätsbibliothek Rostockhttps://purl.uni-rostock.de/rosdok/id00005823Tobias Strauß, Welf Wustlich, Roger Labahnrosdok_id000058161986139832Odvhttps://purl.uni-rostock.de/rosdok/id00005816Preprints aus dem Institut für Mathematik3255797-812/10012-0001 2026-10-13T11:59:22.498Z 2026-10-13T13:19:56.901Z 2026-10-23T13:19:56.910Z editorKE {"identifier":"rosdok/id00005823","type":"local_id","additional":"","service":"MCRLocalID","created":"2026-10-13T11:59:22.508Z"} {"identifier":"urn:nbn:de:gbv:28-rosdok_id00005823-5","type":"dnbUrn","additional":"","service":"RosDokURN","created":"2026-10-13T11:59:22.515Z"} {"identifier":"https://purl.uni-rostock.de/rosdok/id00005823","type":"purl","additional":"","service":"RosDokPURL","created":"2026-10-13T11:59:22.519Z","registrationStarted":"2026-10-13T12:08:17.063Z"} {"identifier":"10.18453/rosdok_id00005823","type":"doi","additional":"","service":"RosDokDOI","created":"2026-10-13T11:59:22.522Z","registrationStarted":"2026-10-13T12:08:16.847Z","registered":"2026-10-13T12:08:18.369Z"} editorKEfulltextfile/rosdok_document_0000027958/rosdok_derivate_0000229884/Strauss_design_2012.pdfDesign strategies for weight matrices of Echo State NetworksDesign strategies for weight matrices of Echo State Networksgnd:1136294554orcid:0000-0002-5344-4188gnd:170999645orcid:0000-0003-1901-9644gnd:1136294554orcid:0000-0002-5344-4188gnd:170999645orcid:0000-0003-1901-9644rosdok_document_0000027958-d4017101e49gnd:1136294554orcid:0000-0002-5344-4188Tobias StraußTobias Straußrosdok_document_0000027958-d4017101e65Welf WustlichWelf Wustlichrosdok_document_0000027958-d4017101e75gnd:170999645orcid:0000-0003-1901-9644Roger LabahnRoger LabahnTobias StraußWelf WustlichRoger LabahnTobias StraußWelf WustlichRoger LabahnTobias StraußWelf WustlichRoger LabahnRostockUniversity of Rostock, Institute of Mathematicsepub.workingpaperhttps://purl.uni-rostock.de/rosdok/id00005823urn:nbn:de:gbv:28-rosdok_id00005823-510.18453/rosdok_id00005823This 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.20122012Preprints aus dem Institut für Mathematikrosdok_id000058161986139832Odvhttps://purl.uni-rostock.de/rosdok/id00005816Preprints aus dem Institut für Mathematik3255797-812/10012-0001https://purl.uni-rostock.de/rosdok/id000058163255797-8Tobias Strauß, Welf Wustlich, Roger Labahn[xslt]Saxonrosdok_id00005823https://purl.uni-rostock.de/rosdok/id00005823198667700110.18453/rosdok_id00005823urn:nbn:de:gbv:28-rosdok_id00005823-5Tobias Strauß, Welf Wustlich, Roger LabahnStrauß Tobias, Wustlich Welf, Labahn RogerDesign strategies for weight matrices of Echo State NetworksWorkingpaperworking paperUniversity of Rostock, Institute of Mathematics, 2012This 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…rosdok_id000058160012-000112/1Tobias StraußWelf WustlichRoger LabahnDesign strategies for weight matrices of Echo State NetworksPreprints aus dem Institut für MathematikUniversitätsbibliothek Rostockhttps://purl.uni-rostock.de/rosdok/id00005823TobiasStrauß1984 -VerfasserInaut11362945540000-0002-5344-4188WelfWustlichVerfasserInautRogerLabahn1959 -VerfasserInaut1709996450000-0003-1901-9644[purl]https://purl.uni-rostock.de/rosdok/id00005823[urn]urn:nbn:de:gbv:28-rosdok_id00005823-5[doi]10.18453/rosdok_id00005823open_access20122012epoch:21th_centuryrfc5646:endoctype:epub.workingpaperaccesscondition:openaccessSDNB:510institution:unirostock.mnfstate:published