Stability analysis of discrete-time recurrent neural networks

IEEE Transactions on Neural Networks

Volumn 13, Issue 2, 2002, Pages 292-303

  Barabanov, Nikita E ^b   Prokhorov, Danil V ^a,c  

^a IEEE

^b SAINT PETERSBURG ELECTROTECHNICAL UNIVERSITY LETI   (Russian Federation)

^c FORD RESEARCH LABORATORY   (United States)

Author keywords

Bias weight; Discrete time recurrent neural network; Exponential stability; Linear matrix inequality (LMI); Lyapunov stability; Recurrent multilayer perceptrons (RMLPs); Recurrent neural network (RNN); Sector monotone nonlinearity; State space transformation

Indexed keywords

APPROXIMATION THEORY; BACKPROPAGATION; KALMAN FILTERING; MULTILAYER NEURAL NETWORKS; STATE SPACE METHODS; SYSTEM STABILITY;

DISCRETE TIME RECURRENT NEURAL NETWORKS; LINEAR MATRIX INEQUALITY (LMI); STABILITY ANALYSIS;

RECURRENT NEURAL NETWORKS;

EID: 0036506134     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.991416     Document Type: Article

References (12)

1. Bounds of the induced norm and model reduction errors for systems with repeated scalar nonlinearities
2. An approach to stability criteria of neural-network control systems
3. A polynomial-time algorithm for determining quadratic Lyapunov functions for nonlinear systems
4. Frequency domain criteria for stability and instability in the large for the stationary sets of nonlinear systems of differential equations with a monotone nonlinearity
5. A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering and classification
6. The method of matrix inequalities in the stability theory of nonlinear control systems
7. Frequency criteria for the absolute stability of nonlinear sampled data systems
8. Interior-Point Polynomial Methods in Convex Programming
9. Linear matrix inequalities in system and control theory
10. Nonlinear system identification using neural networks