KI - Künstliche Intelligenz

, Volume 26, Issue 4, pp 415–416 | Cite as

Reservoir Computing with Output Feedback

A Dynamical System Approach to Inverse Modeling
Dissertationen und Habilitationen

Abstract

This thesis presents a dynamical system approach to learning forward and inverse models in associative recurrent neural networks. Ambiguous inverse models are represented by multi-stable dynamics. Random projection networks, i.e. reservoirs, together with a rigorous regularization methodology enable robust and efficient training of multi-stable dynamics with application to movement control in robotics.

Keywords

Dynamical systems Machine learning 

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  1. 1.BielefeldGermany

Personalised recommendations