Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Developing neural networks with neurons competing for survival

Peng, Z., & Braun, D. (2015). Developing neural networks with neurons competing for survival. In 5th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EPIROB 2015) (pp. 152-153). Piscataway, NJ, USA: IEEE.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-002A-44FE-1 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0000-8104-9
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=arnumber=7346133 (Verlagsversion)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Peng, Z1, Autor           
Braun, DA1, 2, Autor           
Affiliations:
1Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497809              
2Research Group Sensorimotor Learning and Decision-making, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1688138              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We study developmental growth in a feedforward neural network model inspired by the survival principle in nature. Each neuron has to select its incoming connections in a way that allow it to fire, as neurons that are not able to fire over a period of time degenerate and die. In order to survive, neurons have to find reoccurring patterns in the activity of the neurons in the preceding layer, because each neuron requires more than one active input at any one time to have enough activation for firing. The sensory input at the lowest layer therefore provides the maximum amount of activation that all neurons compete for. The whole network grows dynamically over time depending on how many patterns can be found and how many neurons can maintain themselves accordingly. We show in simulations that this naturally leads to abstractions in higher layers that emerge in a unsupervised fashion. When evaluating the network in a supervised learning paradigm, it is clear that our network is not competitive. What is interesting though is that this performance was achieved by neurons that simply struggle for survival and do not know about performance error. In contrast to most studies on neural evolution that rely on a network-wide fitness function, our goal was to show that learning behaviour can appear in a system without being driven by any specific utility function or reward signal.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2015-08
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1109/DEVLRN.2015.7346133
BibTex Citekey: PengB2015
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 5th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EPIROB 2015)
Veranstaltungsort: Providence, RI, USA
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 5th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EPIROB 2015)
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Piscataway, NJ, USA : IEEE
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 152 - 153 Identifikator: ISBN: 978-1-4673-9320-1