Related Experiment Video
Updated: Oct 4, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
Stability Analysis for Delayed Neural Networks via a Generalized Reciprocally Convex Inequality
This study introduces a new method for analyzing the stability of neural networks with time-varying delays. The findings offer improved criteria for ensuring the reliable operation of these complex systems.
Area of Science:
- Control Theory
- Artificial Intelligence
- Dynamical Systems
Background:
- Neural networks (NNs) are crucial in AI, but their stability can be compromised by time-varying delays.
- Ensuring the stability of NNs with time-varying delays is a significant challenge in control theory.
Purpose of the Study:
- To develop novel stability criteria for neural networks with time-varying delays.
- To introduce a generalized reciprocally convex inequality (RCI) for tighter bounds.
- To propose a new Lyapunov-Krasovskii functional (LKF) tailored for delayed NNs.
Main Methods:
- Development of a generalized reciprocally convex inequality (RCI).
- Construction of a novel Lyapunov-Krasovskii functional (LKF) incorporating a generalized delay-product term.
- Derivation of new stability criteria based on the RCI and LKF.
Main Results:
- A generalized RCI is presented, encompassing existing inequalities.
- A novel LKF is constructed for analyzing delayed neural networks.
- New stability criteria for time-delay neural networks are established.
Conclusions:
- The proposed stability criteria are effective for neural networks with time-varying delays.
- The generalized RCI and novel LKF offer advantages in stability analysis.
- Numerical examples validate the proposed methods for delayed NNs.
More Related Videos
08:08Real-time Electrophysiology: Using Closed-loop Protocols to Probe Neuronal Dynamics and Beyond
Published on: June 24, 2015
10:44Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
Published on: December 7, 2021
Related Concept Videos
BIBO stability of continuous and discrete -time systems
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system....
Linear Approximation in Frequency Domain
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
Multimachine Stability
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
Stability
The stability of an LTI system is determined by the roots of its characteristic equation, known as poles. A system is stable if it produces a bounded...
Current Growth And Decay In RL Circuits
Linear time-invariant Systems
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...