Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Delayed standard neural network models for control systems.

Meiqin Liu1

  • 1Department of Systems Science and Engineering, College of Electrical Engineering, Zhejiang University, Hangzhou 310027, PR China. liumeiqin@cee.zju.edu.cn

IEEE Transactions on Neural Networks
|January 29, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Symmetric Entropy-Constrained Video Coding for Machines.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Precision-engineered STING agonist nanoparticles enable coordinated mucosal-systemic immunity for durable pan-β-coronavirus protection.

Nature nanotechnology·2026
Same author

Gamma Knife consolidation therapy improves prognosis in patients with advanced epidermal growth factor receptor-mutant lung adenocarcinoma treated with first-generation epidermal growth factor receptor-tyrosine kinase inhibitors.

Oncology letters·2025
Same author

Morphological Study of First Instar Elephant Stomach Bot Fly Larvae (Oestridae: Gasterophilinae: <i>Cobboldia elephantis</i>).

Insects·2025
Same author

Cooperative Fuzzy Event-Based Tracking Control of Heterogeneous Multiple Marine Vehicles With a Nonautonomous Leader.

IEEE transactions on cybernetics·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A novel Delayed Standard Neural Network Model (DSNNM) simplifies stability analysis for recurrent neural networks (RNNs) and nonlinear systems. This unified approach uses linear matrix inequalities for controller synthesis, enhancing system stability.

Area of Science:

  • Control Theory
  • Artificial Intelligence
  • Nonlinear Systems Analysis

Background:

  • Recurrent Neural Networks (RNNs) and nonlinear systems pose challenges for stability analysis and controller design.
  • Existing methods lack a unified framework for systems with and without time delays.

Purpose of the Study:

  • To introduce the Delayed Standard Neural Network Model (DSNNM) for unified stability analysis and controller synthesis.
  • To develop criteria for global asymptotic and exponential stability of continuous-time and discrete-time DSNNMs.
  • To design state-feedback controllers for stabilizing closed-loop systems incorporating DSNNMs.

Main Methods:

  • The DSNNM is defined as an interconnection of a linear dynamic system and a bounded static nonlinear operator.
  • Lyapunov functionals and the S-procedure are combined to derive stability criteria.

Related Experiment Videos

  • Stability conditions are formulated as Linear Matrix Inequalities (LMIs).

    • Main Results:

    • Novel criteria for global asymptotic and exponential stability of continuous-time and discrete-time DSNNMs are derived.
    • State-feedback control laws are designed based on the derived stability analysis.
    • The DSNNM framework successfully analyzes RNN stability and synthesizes controllers for nonlinear systems.

    Conclusions:

    • The DSNNM provides a unified and convenient approach for analyzing the stability of various RNNs and nonlinear systems.
    • The method simplifies stability verification for RNNs and offers a new perspective for controller synthesis in nonlinear systems.
    • The derived LMIs facilitate practical implementation of stability analysis and controller design.