Reservoir computing with output feedback

Reinhart RF (2011)
Bielefeld: Bielefeld University.

Download
OA
Bielefeld Dissertation | English
Author
Supervisor
Steil, Jochen
Abstract
A dynamical system approach to forward and inverse modeling is proposed. Forward and inverse models are trained in associative recurrent neural networks that are based on non-linear random projections. Feedback of estimated outputs into such reservoir networks is a key ingredient in the context of bidirectional association but entails the problem of error amplification. Robust training of reservoir networks with output feedback is achieved by a novel one-shot learning and regularization method for input-driven recurrent neural networks. It is shown that output feedback enables the implementation of ambiguous inverse models by means of multi-stable dynamics. The proposed methodology is applied to movement generation of robotic manipulators in a feedforward-feedback control framework.
Year
PUB-ID

Cite this

Reinhart RF. Reservoir computing with output feedback. Bielefeld: Bielefeld University; 2011.
Reinhart, R. F. (2011). Reservoir computing with output feedback. Bielefeld: Bielefeld University.
Reinhart, R. F. (2011). Reservoir computing with output feedback. Bielefeld: Bielefeld University.
Reinhart, R.F., 2011. Reservoir computing with output feedback, Bielefeld: Bielefeld University.
R.F. Reinhart, Reservoir computing with output feedback, Bielefeld: Bielefeld University, 2011.
Reinhart, R.F.: Reservoir computing with output feedback. Bielefeld University, Bielefeld (2011).
Reinhart, René Felix. Reservoir computing with output feedback. Bielefeld: Bielefeld University, 2011.
Main File(s)
Access Level
OA Open Access
Last Uploaded
2012-01-19 10:23:43

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar