TY - GEN
T1 - Control of recurrent neural networks using differential minimax game
T2 - ASME 2010 Dynamic Systems and Control Conference, DSCC2010
AU - Liu, Ziqian
AU - Ansari, Nirwan
PY - 2010
Y1 - 2010
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=79958192439&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79958192439&partnerID=8YFLogxK
U2 - 10.1115/DSCC2010-4006
DO - 10.1115/DSCC2010-4006
M3 - Conference contribution
AN - SCOPUS:79958192439
SN - 9780791844182
T3 - ASME 2010 Dynamic Systems and Control Conference, DSCC2010
SP - 491
EP - 497
BT - ASME 2010 Dynamic Systems and Control Conference, DSCC2010
Y2 - 12 September 2010 through 15 September 2010
ER -