Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems

This paper describes how agents can learn an internal model of the world structurally by focusing on the problem of behavior-based articulation. We develop an on-line learning scheme—the so-called mixture of recurrent neural net (RNN) experts—in which a set of RNN modules become self-organized as ex...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 1999-10, Vol.12 (7), p.1131-1141
Hauptverfasser:	Tani, J., Nolfi, S.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Articulation Attentional switch Computer simulation Expert systems Hierarchical learning Hierarchical systems Mixture of experts Recurrent neural networks Sensory perception Sensory-motor systems
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!