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.
- Dynamic Systems and Control Division
Control of Recurrent Neural Networks Using Differential Minimax Game: The Stochastic Case
- Views Icon Views
- Share Icon Share
- Search Site
Liu, Z, & Ansari, N. "Control of Recurrent Neural Networks Using Differential Minimax Game: The Stochastic Case." Proceedings of the ASME 2010 Dynamic Systems and Control Conference. ASME 2010 Dynamic Systems and Control Conference, Volume 2. Cambridge, Massachusetts, USA. September 12–15, 2010. pp. 491-497. ASME. https://doi.org/10.1115/DSCC2010-4006
Download citation file: