Control of recurrent neural networks using differential minimax game: The stochastic case
Document Type
Conference Proceeding
Publication Date
12-1-2010
Abstract
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. Copyright © 2010 by ASME.
Identifier
79958192439 (Scopus)
ISBN
[9780791844182]
Publication Title
ASME 2010 Dynamic Systems and Control Conference Dscc2010
External Full Text Location
https://doi.org/10.1115/DSCC2010-4006
First Page
491
Last Page
497
Volume
2
Recommended Citation
Liu, Ziqian and Ansari, Nirwan, "Control of recurrent neural networks using differential minimax game: The stochastic case" (2010). Faculty Publications. 5957.
https://digitalcommons.njit.edu/fac_pubs/5957