Monostable multivibrators as novel artificial neurons.
Saved in:
| Title: | Monostable multivibrators as novel artificial neurons. |
|---|---|
| Authors: | Keuninckx, Lars1 lkeuninc@ulb.ac.be, Danckaert, Jan1 jan.danckaert@vub.be, Van der Sande, Guy1 guy.van.der.sande@vub.be |
| Source: | Neural Networks. Dec2018, Vol. 108, p224-239. 16p. |
| Subjects: | Neurons, Multivibrators, Relaxation oscillators, Time measurements, Neural circuitry |
| Abstract: | Abstract Retriggerable and non-retriggerable monostable multivibrators are simple timers with a single characteristic, their period. Motivated by the fact that monostable multivibrators are implementable in large quantities as counters in digital programmable hardware, we set out to investigate their applicability as building blocks of artificial neural networks. We derive the nonlinear input–output firing rate relations for single multivibrator neurons as well as the equilibrium firing rate of large recurrent networks. We show that in rate-encoded monostable multivibrators networks the synaptic weights are tunable as the period ratio of connected units, and thus reconfigurable at run time in a counter-based digital implementation. This is illustrated with the task of handwritten digit recognition. Furthermore, we show in a task-independent manner that networks of monostable multivibrators are capable of nonlinear separation, when operating directly on pulse streams. Our research implies that pulse-coupled neural networks with excitable neurons showing a delayed response can perform computations even when working solely with suprathreshold pulses. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Networks is the property of Pergamon Press - An Imprint of Elsevier Science 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: 133047554 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Monostable multivibrators as novel artificial neurons. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Keuninckx%2C+Lars%22">Keuninckx, Lars</searchLink><relatesTo>1</relatesTo><i> lkeuninc@ulb.ac.be</i><br /><searchLink fieldCode="AR" term="%22Danckaert%2C+Jan%22">Danckaert, Jan</searchLink><relatesTo>1</relatesTo><i> jan.danckaert@vub.be</i><br /><searchLink fieldCode="AR" term="%22Van+der+Sande%2C+Guy%22">Van der Sande, Guy</searchLink><relatesTo>1</relatesTo><i> guy.van.der.sande@vub.be</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neural+Networks%22">Neural Networks</searchLink>. Dec2018, Vol. 108, p224-239. 16p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Neurons%22">Neurons</searchLink><br /><searchLink fieldCode="DE" term="%22Multivibrators%22">Multivibrators</searchLink><br /><searchLink fieldCode="DE" term="%22Relaxation+oscillators%22">Relaxation oscillators</searchLink><br /><searchLink fieldCode="DE" term="%22Time+measurements%22">Time measurements</searchLink><br /><searchLink fieldCode="DE" term="%22Neural+circuitry%22">Neural circuitry</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Abstract Retriggerable and non-retriggerable monostable multivibrators are simple timers with a single characteristic, their period. Motivated by the fact that monostable multivibrators are implementable in large quantities as counters in digital programmable hardware, we set out to investigate their applicability as building blocks of artificial neural networks. We derive the nonlinear input–output firing rate relations for single multivibrator neurons as well as the equilibrium firing rate of large recurrent networks. We show that in rate-encoded monostable multivibrators networks the synaptic weights are tunable as the period ratio of connected units, and thus reconfigurable at run time in a counter-based digital implementation. This is illustrated with the task of handwritten digit recognition. Furthermore, we show in a task-independent manner that networks of monostable multivibrators are capable of nonlinear separation, when operating directly on pulse streams. Our research implies that pulse-coupled neural networks with excitable neurons showing a delayed response can perform computations even when working solely with suprathreshold pulses. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neural Networks is the property of Pergamon Press - An Imprint of Elsevier Science 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=133047554 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.neunet.2018.08.014 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 16 StartPage: 224 Subjects: – SubjectFull: Neurons Type: general – SubjectFull: Multivibrators Type: general – SubjectFull: Relaxation oscillators Type: general – SubjectFull: Time measurements Type: general – SubjectFull: Neural circuitry Type: general Titles: – TitleFull: Monostable multivibrators as novel artificial neurons. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Keuninckx, Lars – PersonEntity: Name: NameFull: Danckaert, Jan – PersonEntity: Name: NameFull: Van der Sande, Guy IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2018 Type: published Y: 2018 Identifiers: – Type: issn-print Value: 08936080 Numbering: – Type: volume Value: 108 Titles: – TitleFull: Neural Networks Type: main |
| ResultId | 1 |
