Summary: CONTROL OF RECURRENT NEURAL NETWORKS USING DIFFERENTIAL MINIMAX GAME:
THE STOCHASTIC CASE
Ziqian Liu
Department of Engineering
State University of New York Maritime College
Throggs Neck, NY 10465
zliu@sunymaritime.edu
Nirwan Ansari
Department of Electrical & Computer Engineering
New Jersey Institute of Technology
Newark, New Jersey, 07102
Nirwan.Ansari@njit.edu
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

Source: Ansari, Nirwan - Department of Electrical and Computer Engineering, New Jersey Institute of Technology

Collections: Engineering