The Asymptotic Performance of Linear Echo State Neural Networks
| Title: | The Asymptotic Performance of Linear Echo State Neural Networks |
|---|---|
| Authors: | Couillet, Romain, Wainrib, Gilles, Sevi, Harry, Ali, Hafiz Tiomoko |
| Publication Year: | 2016 |
| Collection: | Computer Science Mathematics |
| Subject Terms: | Computer Science - Learning, Computer Science - Neural and Evolutionary Computing, Mathematics - Probability |
| More Details: | In this article, a study of the mean-square error (MSE) performance of linear echo-state neural networks is performed, both for training and testing tasks. Considering the realistic setting of noise present at the network nodes, we derive deterministic equivalents for the aforementioned MSE in the limit where the number of input data $T$ and network size $n$ both grow large. Specializing then the network connectivity matrix to specific random settings, we further obtain simple formulas that provide new insights on the performance of such networks. |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/1603.07866 |
| Accession Number: | edsarx.1603.07866 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/1603.07866 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20160325&spage=&pages=&title=The Asymptotic Performance of Linear Echo State Neural Networks&atitle=The%20Asymptotic%20Performance%20of%20Linear%20Echo%20State%20Neural%20Networks&aulast=Couillet%2C%20Romain&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.1603.07866 RelevancyScore: 954 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 953.507202148438 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: The Asymptotic Performance of Linear Echo State Neural Networks – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Couillet%2C+Romain%22">Couillet, Romain</searchLink><br /><searchLink fieldCode="AR" term="%22Wainrib%2C+Gilles%22">Wainrib, Gilles</searchLink><br /><searchLink fieldCode="AR" term="%22Sevi%2C+Harry%22">Sevi, Harry</searchLink><br /><searchLink fieldCode="AR" term="%22Ali%2C+Hafiz+Tiomoko%22">Ali, Hafiz Tiomoko</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2016 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science<br />Mathematics – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Learning%22">Computer Science - Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Neural+and+Evolutionary+Computing%22">Computer Science - Neural and Evolutionary Computing</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematics+-+Probability%22">Mathematics - Probability</searchLink> – Name: Abstract Label: Description Group: Ab Data: In this article, a study of the mean-square error (MSE) performance of linear echo-state neural networks is performed, both for training and testing tasks. Considering the realistic setting of noise present at the network nodes, we derive deterministic equivalents for the aforementioned MSE in the limit where the number of input data $T$ and network size $n$ both grow large. Specializing then the network connectivity matrix to specific random settings, we further obtain simple formulas that provide new insights on the performance of such networks. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/1603.07866" linkWindow="_blank">http://arxiv.org/abs/1603.07866</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.1603.07866 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.1603.07866 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Learning Type: general – SubjectFull: Computer Science - Neural and Evolutionary Computing Type: general – SubjectFull: Mathematics - Probability Type: general Titles: – TitleFull: The Asymptotic Performance of Linear Echo State Neural Networks Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Couillet, Romain – PersonEntity: Name: NameFull: Wainrib, Gilles – PersonEntity: Name: NameFull: Sevi, Harry – PersonEntity: Name: NameFull: Ali, Hafiz Tiomoko IsPartOfRelationships: – BibEntity: Dates: – D: 25 M: 03 Type: published Y: 2016 |
| ResultId | 1 |