TY  - THES
AB  - 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.
DA  - 2011
KW  - bidirectional association
KW  - recurrent neural networks
KW  - regularization
KW  - stability
KW  - inverse models
LA  - eng
PY  - 2011
TI  - Reservoir computing with output feedback
UR  - https://nbn-resolving.org/urn:nbn:de:hbz:361-24594130
Y2  - 2024-11-22T08:54:20
ER  -