Convergence Criteria for a Hopfield-type Neural Network

2005/03/17 by Raveen Goundar, Goundar, Raveen, Jito Vanualailai +1
Mathematics · #34D20 #92B20 #Classical Analysis and ODEs (math.CA) #Dynamical Systems (math.DS) #FOS: Mathematics #math.CA #math.DS #msc:34D20 #msc:92B20

paper · pdf · doi:10.48550/arxiv.math/0503361

15 pages

arxiv created 2005/03/17 · arxiv updated 2009/12/01

Abstract

Motivated by recent applications of the Lyapunov's method in artificial neural networks, which could be considered as dynamical systems for which the convergence of the system trajectories to equilibrium states is a necessity. We re-look at a well-known Krasovskii's stability criteria pertaining to a non linear autonomous system. Instead, we consider the components of the same autonomous system with the help of the elements of Jacobian matrix J(x), thus proposing much simpler convergence criteria via the method of Lyapunov. We then apply our results to artificial neural networks and discuss our results with respect to recent ones in the field.

Related

• Global Convergence of Analytic Neural Networks with Event-triggered Synaptic Feedbacks
• Approximation and decomposition of attractors of a Hopfield neural network system
• Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions
• Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation
• Iterative Neural Networks with Bounded Weights