Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Learning programs is better than learning dynamics: A programmable neural network hierarchical architecture in a multi-task scenario
KTH, School of Industrial Engineering and Management (ITM), Production Engineering.ORCID iD: 0000-0001-6064-5634
Show others and affiliations
2015 (English)In: Adaptive Behavior, ISSN 1059-7123, E-ISSN 1741-2633, Vol. 24, no 1, 27-51 p.Article in journal (Refereed) Published
Abstract [en]

Distributed and hierarchical models of control are nowadays popular in computational modeling and robotics. In the artificial neural network literature, complex behaviors can be produced by composing elementary building blocks or motor primitives, possibly organized in a layered structure. However, it is still unknown how the brain learns and encodes multiple motor primitives, and how it rapidly reassembles, sequences and switches them by exerting cognitive control. In this paper we advance a novel proposal, a hierarchical programmable neural network architecture, based on the notion of programmability and an interpreter-programmer computational scheme. In this approach, complex (and novel) behaviors can be acquired by embedding multiple modules (motor primitives) in a single, multi-purpose neural network. This is supported by recent theories of brain functioning in which skilled behaviors can be generated by combining functional different primitives embedded in “reusable” areas of “recycled” neurons. Such neuronal substrate supports flexible cognitive control, too. Modules are seen as interpreters of behaviors having controlling input parameters, or programs that encode structures of networks to be interpreted. Flexible cognitive control can be exerted by a programmer module feeding the interpreters with appropriate input parameters, without modifying connectivity. Our results in a multiple T -maze robotic scenario show how this computational framework provides a robust, scalable and flexible scheme that can be iterated at different hierarchical layers permitting to learn, encode and control multiple qualitatively different behaviors.

Place, publisher, year, edition, pages
2015. Vol. 24, no 1, 27-51 p.
Keyword [en]
Programming neural networks, hierarchical organization, distributed representation, neuronal reuse, cognitive control
National Category
Other Computer and Information Science Other Computer and Information Science
Identifiers
URN: urn:nbn:se:kth:diva-177627DOI: 10.1177/1059712315609412ISI: 000370374700003Scopus ID: 2-s2.0-84957824197OAI: oai:DiVA.org:kth-177627DiVA: diva2:873772
Note

QC 20160211. QC 20160319

Available from: 2015-11-24 Created: 2015-11-24 Last updated: 2017-12-01Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopushttp://adb.sagepub.com/content/24/1/27

Authority records BETA

de Giorgio, Andrea

Search in DiVA

By author/editor
de Giorgio, Andrea
By organisation
Production Engineering
In the same journal
Adaptive Behavior
Other Computer and Information ScienceOther Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 156 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf