Show simple item record

dc.contributor.authorCarmantini, GS
dc.contributor.authorbeim Graben, P
dc.contributor.authorDesroches, M
dc.contributor.authorRodrigues, S
dc.date.accessioned2016-11-10T17:38:48Z
dc.date.available2016-11-10T17:38:48Z
dc.date.issued2017-01-01
dc.identifier.issn0893-6080
dc.identifier.issn1879-2782
dc.identifier.otherC
dc.identifier.urihttp://hdl.handle.net/10026.1/6710
dc.descriptionpublisher: Elsevier articletitle: A modular architecture for transparent computation in recurrent neural networks journaltitle: Neural Networks articlelink: http://dx.doi.org/10.1016/j.neunet.2016.09.001 content_type: article copyright: © 2016 Elsevier Ltd. All rights reserved.
dc.description.abstract

Computation is classically studied in terms of automata, formal languages and algorithms; yet, the relation between neural dynamics and symbolic representations and operations is still unclear in traditional eliminative connectionism. Therefore, we suggest a unique perspective on this central issue, to which we would like to refer as transparent connectionism, by proposing accounts of how symbolic computation can be implemented in neural substrates. In this study we first introduce a new model of dynamics on a symbolic space, the versatile shift, showing that it supports the real-time simulation of a range of automata. We then show that the Gödelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space. Finally, we present a mapping between nonlinear dynamical automata and recurrent artificial neural networks. The mapping defines an architecture characterized by its granular modularity, where data, symbolic operations and their control are not only distinguishable in activation space, but also spatially localizable in the network itself, while maintaining a distributed encoding of symbolic representations. The resulting networks simulate automata in real-time and are programmed directly, in the absence of network training. To discuss the unique characteristics of the architecture and their consequences, we present two examples: (i) the design of a Central Pattern Generator from a finite-state locomotive controller, and (ii) the creation of a network simulating a system of interactive automata that supports the parsing of garden-path sentences as investigated in psycholinguistics experiments.

dc.format.extent85-105
dc.format.mediumPrint-Electronic
dc.languageen
dc.language.isoen
dc.publisherElsevier BV
dc.subjectAutomata Theory
dc.subjectRecurrent artificial neural networks
dc.subjectRepresentation theory
dc.subjectNonlinear dynamical automata
dc.subjectNeural symbolic computation
dc.subjectVersatile shift
dc.titleA modular architecture for transparent computation in recurrent neural networks
dc.typejournal-article
dc.typeArticle
plymouth.author-urlhttps://www.ncbi.nlm.nih.gov/pubmed/27814468
plymouth.volume85
plymouth.publisher-urlhttp://dx.doi.org/10.1016/j.neunet.2016.09.001
plymouth.publication-statusAccepted
plymouth.journalNeural Networks
dc.identifier.doi10.1016/j.neunet.2016.09.001
plymouth.organisational-group/Plymouth
plymouth.organisational-group/Plymouth/Faculty of Science and Engineering
dc.publisher.placeUnited States
dcterms.dateAccepted2016-09-05
dc.rights.embargodate2017-9-24
dc.identifier.eissn1879-2782
dc.rights.embargoperiodNot known
rioxxterms.versionofrecord10.1016/j.neunet.2016.09.001
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2017-01-01
rioxxterms.typeJournal Article/Review


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record


All items in PEARL are protected by copyright law.
Author manuscripts deposited to comply with open access mandates are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author.
Theme by 
Atmire NV