Autonomous learning needs a second environmental feedback loop
DC Element | Wert | Sprache |
---|---|---|
dc.contributor.author | Toutounji, H. | |
dc.contributor.author | Pasemann, F. | |
dc.date.accessioned | 2021-12-23T16:32:17Z | - |
dc.date.available | 2021-12-23T16:32:17Z | - |
dc.date.issued | 2016 | |
dc.identifier.issn | 1860949X | |
dc.identifier.uri | https://osnascholar.ub.uni-osnabrueck.de/handle/unios/17283 | - |
dc.description.abstract | Deriving a successful neural control of behavior of autonomous and embodied systems poses a great challenge. The difficulty lies in finding suitable learning mechanisms, and in specifying under what conditions learning becomes necessary.Here, we provide a solution to the second issue in the form of an additional feedback loop that augments the sensorimotor loop in which autonomous systems live. The second feedback loop provides proprioceptive signals, allowing the assessment of behavior through self-monitoring, and accordingly, the control of learning. We show how the behaviors can be defined with the aid of this framework, and we show that, in combination with simple stochastic plasticity mechanisms, behaviors are successfully learned. © Springer International Publishing Switzerland 2016. | |
dc.description.sponsorship | Deutsche ForschungsgemeinschaftDeutsche Forschungsgemeinschaft,DFG; This research was partially funded by the German Research Foundation (DFG) priority program 1527. The contribution of Christian Rempis to this project is gratefully acknowledged. The authors thank Josef Behr, Andrea Suckro, and Florian Ziegler for testing and refining the simulation models in the NERD Toolkit, and particularly the latter for his role in the current study. Thanks to Kevin Koschmieder for implementing the modulated Gaussian walk. | |
dc.language.iso | en | |
dc.publisher | Springer Verlag | |
dc.relation.ispartof | Studies in Computational Intelligence | |
dc.subject | Auton-omous systems | |
dc.subject | Learning | |
dc.subject | Neuromodulation | |
dc.subject | Plasticity | |
dc.subject | Sensorimotor loop | |
dc.title | Autonomous learning needs a second environmental feedback loop | |
dc.type | book part | |
dc.identifier.doi | 10.1007/978-3-319-23392-5_25 | |
dc.identifier.scopus | 2-s2.0-84947736904 | |
dc.identifier.url | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84947736904&doi=10.1007%2f978-3-319-23392-5_25&partnerID=40&md5=6e43c946e44deb3ba5aedea093ed4166 | |
dc.description.volume | 613 | |
dc.description.startpage | 455 | |
dc.description.endpage | 472 | |
dcterms.isPartOf.abbreviation | Stud. Comput. Intell. |
Seitenaufrufe
4
Letzte Woche
0
0
Letzter Monat
0
0
geprüft am 08.06.2024