A new robust training law for dynamic neural networks with external disturbance: an LMI approach

DOI10.1155/2010/415895MaRDI QIDQ624433zbMATH OpenOpenAlexWikidataFDO

Authors Choon Ki Ahn

Publication date 9 February 2011

Published in Discrete Dynamics in Nature and Society (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://eudml.org/doc/231292

zbMATH Keywords

dynamic neural networksexponential stabilityexternal disturbanceinput/output-to-state stable traininglinear matrix inequalityrobust training

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Perturbations in control/observation systems (93C73) Asymptotic stability in control theory (93D20) Input-output approaches in control theory (93D25)

Review text

Summary: A new robust training law, which is called an Input/Output-to-State Stable Training Law (IOSSTL), is proposed for dynamic neural networks with external disturbance. Based on Linear Matrix Inequality (LMI) formulation, the IOSSTL is presented to not only guarantee exponential stability but also reduce the effect of an external disturbance. It is shown that the IOSSTL can be obtained by solving the LMI, which can be easily facilitated by using some standard numerical packages. Numerical examples are presented to demonstrate the validity of the proposed IOSSTL.

Recommendations

• Robust stability of recurrent neural networks with ISS learning algorithm
• Robust adaptive learning of feedforward neural networks via LMI optimizations
• An \(H_\infty\) control approach to robust learning of feedforward neural networks
• Input-to-state stability (ISS) analysis for dynamic neural networks
• Robust control of dynamical systems using neural networks with input–output feedback linearization

Cites work

• A simple proof of a necessary and sufficient condition for absolute stability of symmetric neural networks
• Adaptive control of chaos in Lorenz system
• Adaptive control of unknown plants using dynamical neural networks
• Asymptotic characterizations of input- output-to-state stability for discrete-time systems
• Changing supply rates for input-output to state stable discrete-time nonlinear systems with applications
• Identification of nonlinear dynamical systems using multilayered neural networks
• Input-output-to-state stability
• Input-output-to-state stability for discrete-time systems
• Input-to-state stability (ISS) analysis for dynamic neural networks
• Lur'e systems with multilayer perceptron and recurrent neural networks: absolute stability and dissipativity
• Necessary and Sufficient Conditions for Analysis and Synthesis of Markov Jump Linear Systems With Incomplete Transition Descriptions
• Neural networks for control systems - a survey
• Neurons with graded response have collective computational properties like those of two-state neurons
• New necessary and sufficient conditions for absolute stability of neural networks
• Output-to-state stability and detectability of nonlinear systems
• Separation Principles for Input-Output and Integral-Input-to-State Stability
• Some stability properties of dynamic neural networks
• Stability and stabilization of Markovian jump linear systems with partly unknown transition probabilities

Cited in

(2)

• Input-to-state stability for dynamical neural networks with time-varying delays
• Robust stability of recurrent neural networks with ISS learning algorithm

This page was built for publication: A new robust training law for dynamic neural networks with external disturbance: an LMI approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q624433)