Title :
Meta-Learning for Adaptive Identification of Non-Linear Dynamical Systems
Author :
Oubbati, Mohamed ; Levi, Paul ; Schanz, Michael
Author_Institution :
Dept. of Image Understanding, Stuttgart Univ.
Abstract :
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
Keywords :
identification; neurocontrollers; nonlinear dynamical systems; recurrent neural nets; adaptive identification; meta-learning; nonlinear dynamical system; recurrent neural network; Autoregressive processes; Control systems; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Recurrent neural networks; Switches; System identification; Velocity control;
Conference_Titel :
Intelligent Control, 2005. Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation
Conference_Location :
Limassol
Print_ISBN :
0-7803-8936-0
DOI :
10.1109/.2005.1467061
