| |
| description |
Adaptive Identification of Non-linear Dynamical Systems via
Recurrent Neural Networks (RNNs) is presented in this paper. We
explore the notion that a fixed-weight RNN needs to change only its
internal state to change its behavior policy. This ability is
acquired through prior training procedure that enable the learning
of adaptive behaviors. Some simulation results are presented.
|
| publisher |
Limassol, Cyprus: IEEE
|
| type |
Text
|
| Article in Proceedings
|
| source |
In: Proceedings of the Joint 20th IEEE International Symposium on
Intelligent Control & 13th Mediterranean Conference on Control
and Automation (2005 ISIC-MED)., pp. 473-478
|
| contributor |
IPVS, Bildverstehen
|
| subject |
Problem Solving, Control Methods, and Search (CR I.2.8)
|
| Adaptive Identification
|
| RNNs
|
| Non-linear Dynamical Systems
|
| Meta-learning.
|
| relation |
IEEE
|