Stabilization of stochastic recurrent neural networks via inverse optimal control

被引：0

作者：

Sanchez, EN ^{[1
]}

Perez, JP ^{[1
]}

Chen, GR ^{[1
]}

机构：

[1] CINVESTAV, Unidad Guadalajara, Guadalajara 45091, Jalisco, Mexico

来源：

PROCEEDINGS OF THE 41ST IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4 | 2002年

关键词：

neural networks; nonlinear systems; stochastic systems; inverse optimal control; Lyapunov function;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The paper studies the stabilization problem for a dynamic neural network disturbed by additive noise. The stabilization is achieved from the inverse optimal control approach, recently introduced in nonlinear control theory, using a quadratic Lyapunov function. A simple feedback control law is derived, which ensures that the neural network state is globally asymptotically stable in probability.

引用

页码：1762 / 1763

页数：2

共 4 条

[1] Noisy recurrent neural networks: The continuous-time case [J].

Das, S ;

Olurotimi, O .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (05) :913-936

[2] NECESSARY AND SUFFICIENT CONDITION FOR ABSOLUTE STABILITY OF NEURAL NETWORKS [J].

FORTI, M ;

MANETTI, S ;

MARINI, M .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1994, 41 (07) :491-494

[3]

Krstic Miroslav., 1998, Stabilization of nonlinear uncertain systems, V1st

[4] Input-to-state stability (ISS) analysis for dynamic neural networks [J].

Sanchez, EN ;

Perez, JP .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1999, 46 (11) :1395-1398

← 1 →