Intrinsic plasticity via natural gradient descent with application to drift compensation.
Saved in:
| Title: | Intrinsic plasticity via natural gradient descent with application to drift compensation. |
|---|---|
| Authors: | Neumann, K.1 kneumann@cor-lab.uni-bielefeld.de, Strub, C.1 cstrub@techfak.uni-bielefeld.de, Steil, J.J.1 jsteil@cor-lab.uni-bielefeld.de |
| Source: | Neurocomputing. Jul2013, Vol. 112, p26-33. 8p. |
| Subjects: | Machine learning, Material plasticity, Information theory, Geometric analysis, Performance evaluation, Comparative studies |
| Abstract: | Abstract: This paper investigates the learning dynamics of intrinsic plasticity (IP), which is a learning rule to tune a neuron's activation function such that its output distribution becomes approximately exponentially distributed. The information-geometric properties of intrinsic plasticity are analyzed and the improved natural gradient intrinsic plasticity (NIP) dynamics are evaluated for a variety of input distributions. Together with a further new modification of the IP rule, the high capability of NIP to cope with drift is demonstrated to have superior performance as compared to the standard gradient in experiments with synthetic and real world data. [Copyright &y& Elsevier] |
| Copyright of Neurocomputing is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 89248259 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Intrinsic plasticity via natural gradient descent with application to drift compensation. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Neumann%2C+K%2E%22">Neumann, K.</searchLink><relatesTo>1</relatesTo><i> kneumann@cor-lab.uni-bielefeld.de</i><br /><searchLink fieldCode="AR" term="%22Strub%2C+C%2E%22">Strub, C.</searchLink><relatesTo>1</relatesTo><i> cstrub@techfak.uni-bielefeld.de</i><br /><searchLink fieldCode="AR" term="%22Steil%2C+J%2EJ%2E%22">Steil, J.J.</searchLink><relatesTo>1</relatesTo><i> jsteil@cor-lab.uni-bielefeld.de</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neurocomputing%22">Neurocomputing</searchLink>. Jul2013, Vol. 112, p26-33. 8p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Material+plasticity%22">Material plasticity</searchLink><br /><searchLink fieldCode="DE" term="%22Information+theory%22">Information theory</searchLink><br /><searchLink fieldCode="DE" term="%22Geometric+analysis%22">Geometric analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Performance+evaluation%22">Performance evaluation</searchLink><br /><searchLink fieldCode="DE" term="%22Comparative+studies%22">Comparative studies</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Abstract: This paper investigates the learning dynamics of intrinsic plasticity (IP), which is a learning rule to tune a neuron's activation function such that its output distribution becomes approximately exponentially distributed. The information-geometric properties of intrinsic plasticity are analyzed and the improved natural gradient intrinsic plasticity (NIP) dynamics are evaluated for a variety of input distributions. Together with a further new modification of the IP rule, the high capability of NIP to cope with drift is demonstrated to have superior performance as compared to the standard gradient in experiments with synthetic and real world data. [Copyright &y& Elsevier] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neurocomputing is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=89248259 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.neucom.2012.12.047 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 8 StartPage: 26 Subjects: – SubjectFull: Machine learning Type: general – SubjectFull: Material plasticity Type: general – SubjectFull: Information theory Type: general – SubjectFull: Geometric analysis Type: general – SubjectFull: Performance evaluation Type: general – SubjectFull: Comparative studies Type: general Titles: – TitleFull: Intrinsic plasticity via natural gradient descent with application to drift compensation. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Neumann, K. – PersonEntity: Name: NameFull: Strub, C. – PersonEntity: Name: NameFull: Steil, J.J. IsPartOfRelationships: – BibEntity: Dates: – D: 18 M: 07 Text: Jul2013 Type: published Y: 2013 Identifiers: – Type: issn-print Value: 09252312 Numbering: – Type: volume Value: 112 Titles: – TitleFull: Neurocomputing Type: main |
| ResultId | 1 |
