Sign in Subscribe
Artificial neural networks

Research from Yantai University Explores Novel Synchronization Behavior in Delayed Fractional-Order Neural Networks

Strategic Insights

— 1 min read

Researchers from Yantai University have made a significant discovery in the field of thermodynamics, investigating the synchronization control problem for delayed fractional-order neural networks (DFONNs) with mismatched parameters. According to a new report, the study proposes a novel synchronization behavior termed quasi-Mittag-Leffler projective synchronization (QMLPS), which offers a more general framework incorporating existing synchronization concepts. The research demonstrates the effectiveness of the theoretical results through numerical simulations, providing insights into the synchronization behaviors of the controlled system under both mismatched and matched parameter conditions.

Key Takeaways:

  • The study introduces a novel synchronization behavior, quasi-Mittag-Leffler projective synchronization (QMLPS), which is more general and incorporates existing synchronization concepts.
  • The research considers the time delay and mismatched parameters between driven and response systems, making it more practical and applicable.
  • The study designs both static controllers and adaptive controllers to synchronize DFONNs, with the synchronization errors estimated and the rate of convergence clarified.
  • The Lyapunov stability theory and fractional-order differential inequalities are used to derive sufficient conditions for DFONNs under two kinds of control methods.
  • Quantitative numerical simulations demonstrate the superiority of the proposed controller, verifying the effectiveness of the theoretical results.

Statistics:

  • The research focuses on delayed fractional-order neural networks (DFONNs) with mismatched parameters.
  • The study proposes a novel synchronization behavior, quasi-Mittag-Leffler projective synchronization (QMLPS).
  • The researchers used the Lyapunov stability theory and fractional-order differential inequalities to derive sufficient conditions for DFONNs.
  • The numerical simulation section verifies the effectiveness of the theoretical results, providing several types of synchronization behaviors of the controlled system.
  • The bound of synchronization errors is estimated by the Mittag-Leffler function.

Sources:

  • Quasi-Mittag-Leffler Projective Synchronization of Delayed Chaotic Fractional Order Neural Network with Mismatched Parameters. Fractal and Fractional, 2025,9(6):379. (Fractal and Fractional - http://www.mdpi.com/journal/fractalfract)
  • Yantai University, School of Mathematics and Information Science, Yantai 264005, People's Republic of China
  • Yongqing Yang, Additional authors of the research
  • Xin Sui, Corresponding author, School of Mathematics and Information Science, Yantai University, Yantai 264005, People's Republic of China

Read more