Title :
Discrete-time systems neuro-Riccati equation solution
Author :
Tamariz, Annabell D R ; Bottura, Celso P.
Author_Institution :
Nucleus of Res. & Dev. in Comput. Sci., Cndido Mendes Univ., Brazil
fDate :
July 31 2005-Aug. 4 2005
Abstract :
In this article proposal for solving the discrete-time algebraic Riccati equation (DARE) using a multilayer recurrent neural network (RNN) approach is presented. Systems of coupled matricial nonlinear differential equations are derived describing the neural dynamics of the Neuro-riccati equation. By solving these coupled matrix equations using recurrent neural networks a symmetric and positive definite solution is obtained. Several examples demonstrate the effectiveness of this proposal and respective implementation.
Keywords :
Riccati equations; discrete time systems; neurocontrollers; nonlinear differential equations; recurrent neural nets; discrete-time algebraic Riccati equation; discrete-time system; multilayer recurrent neural network; neuro-Riccati equation solution; nonlinear differential equations; Computer networks; Control systems; Couplings; Differential algebraic equations; Multi-layer neural network; Nonlinear equations; Proposals; Recurrent neural networks; Riccati equations; Symmetric matrices;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1556253
