Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Recurrent neural networks from learning attractor dynamics

Schaal, S., & Peters, J. (2003). Recurrent neural networks from learning attractor dynamics. Talk presented at NIPS 2003 Workshop on RNNaissance: Recurrent Neural Networks. Whistler, BC, Canada.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Schaal, S, Autor
Peters, J1, 2, Autor           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Many forms of recurrent neural networks can be understood in terms of dynamic systems theory of difference equations or differential equations. Learning in such systems corresponds to adjusting some internal parameters to obtain a desired time evolution of the network, which can usually be characterized in term of point attractor dynamics, limit cycle dynamics, or, in some more rare cases, as strange attractor or chaotic dynamics. Finding a stable learning process to adjust the open parameters of the network towards shaping the desired attractor type and basin of attraction has remain a complex task, as the parameter trajectories during learning can lead the system through a variety of undesirable unstable behaviors, such that learning may never succeed. In this presentation, we review a recently developed learning framework for a class of recurrent neural networks that employs a more structured network approach. We assume that the canonical system behavior is known a priori, e.g., it is a point attractor or a limit cycle. With either supervised learning or reinforcement learning, it is possible to acquire the transformation from a simple representative of this canonical behavior (e.g., a 2nd order linear point attractor, or a simple limit cycle oscillator) to the desired highly complex attractor form. For supervised learning, one shot learning based on locally weighted regression techniques is possible. For reinforcement learning, stochastic policy gradient techniques can be employed. In any case, the recurrent network learned by these methods inherits the stability properties of the simple dynamic system that underlies the nonlinear transformation, such that stability of the learning approach is not a problem. We demonstrate the success of this approach for learning various skills on a humanoid robot, including tasks that require to incorporate additional sensory signals as coupling terms to modify the recurrent network evolution on-line.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2003-12
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: URI: http://www.idsia.ch/~juergen/rnnaissance.html
BibTex Citekey: SchaalP2003
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: NIPS 2003 Workshop on RNNaissance: Recurrent Neural Networks
Veranstaltungsort: Whistler, BC, Canada
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: