Approximate Synchronization of Memristive Hopfield Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: You, Yuncheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918075150893056
author You, Yuncheng
author_facet You, Yuncheng
contents Asymptotic synchronization is one of the essential differences between artificial neural networks and biologically inspired neural networks due to mismatches from dynamical update of weight parameters and heterogeneous activations. In this paper a new concept of approximate synchronization is proposed and investigated for Hopfield neural networks coupled with nonlinear memristors. It is proved that global solution dynamics are robustly dissipative and a sharp ultimate bound is acquired. Through \emph{a priori} uniform estimates on the interneuron differencing equations, it is rigorously shown that approximate synchronization to any prescribed small gap at an exponential convergence rate of the memristive Hopfield neural networks occurs if an explicitly computable threshold condition is satisfied by the interneuron coupling strength coefficient. The main result is further extended to memristive Hopfield neural networks with Hebbian learning rules for a broad range of applications in unsupervised train learning.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Approximate Synchronization of Memristive Hopfield Neural Networks
You, Yuncheng
Analysis of PDEs
34D06, 34D45, 37N25, 68T07, 92B20
Asymptotic synchronization is one of the essential differences between artificial neural networks and biologically inspired neural networks due to mismatches from dynamical update of weight parameters and heterogeneous activations. In this paper a new concept of approximate synchronization is proposed and investigated for Hopfield neural networks coupled with nonlinear memristors. It is proved that global solution dynamics are robustly dissipative and a sharp ultimate bound is acquired. Through \emph{a priori} uniform estimates on the interneuron differencing equations, it is rigorously shown that approximate synchronization to any prescribed small gap at an exponential convergence rate of the memristive Hopfield neural networks occurs if an explicitly computable threshold condition is satisfied by the interneuron coupling strength coefficient. The main result is further extended to memristive Hopfield neural networks with Hebbian learning rules for a broad range of applications in unsupervised train learning.
title Approximate Synchronization of Memristive Hopfield Neural Networks
topic Analysis of PDEs
34D06, 34D45, 37N25, 68T07, 92B20
url https://arxiv.org/abs/2506.23279