Control of Recurrent Neural Networks Using Differential Minimax Game: The Stochastic Case
Keyword(s):
As a continuation of our study, this paper extends our research results of optimality-oriented stabilization from deterministic recurrent neural networks to stochastic recurrent neural networks, and presents a new approach to achieve optimally stochastic input-to-state stabilization in probability for stochastic recurrent neural networks driven by noise of unknown covariance. This approach is developed by using stochastic differential minimax game, Hamilton-Jacobi-Isaacs (HJI) equation, inverse optimality, and Lyapunov technique. A numerical example is given to demonstrate the effectiveness of the proposed approach.
2009 ◽
Vol 72
(10-12)
◽
pp. 2563-2568
◽
Keyword(s):
2008 ◽
Vol 19
(8)
◽
pp. 1389-1401
◽
Keyword(s):
2007 ◽
Vol 221
(8)
◽
pp. 1101-1121
◽
Keyword(s):
2006 ◽
Vol 55
(5)
◽
pp. 385-395
◽
Keyword(s):