Thermodynamics-Inspired Computing with Oscillatory Neural Networks for Inverse Matrix Computation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tsormpatzoglou, George, Sabo, Filip, Todri-Sanial, Aida
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916870960971776
author Tsormpatzoglou, George
Sabo, Filip
Todri-Sanial, Aida
author_facet Tsormpatzoglou, George
Sabo, Filip
Todri-Sanial, Aida
contents We describe a thermodynamic-inspired computing paradigm based on oscillatory neural networks (ONNs). While ONNs have been widely studied as Ising machines for tackling complex combinatorial optimization problems, this work investigates their feasibility in solving linear algebra problems, specifically the inverse matrix. Grounded in thermodynamic principles, we analytically demonstrate that the linear approximation of the coupled Kuramoto oscillator model leads to the inverse matrix solution. Numerical simulations validate the theoretical framework, and we examine the parameter regimes that computation has the highest accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thermodynamics-Inspired Computing with Oscillatory Neural Networks for Inverse Matrix Computation
Tsormpatzoglou, George
Sabo, Filip
Todri-Sanial, Aida
Machine Learning
Emerging Technologies
We describe a thermodynamic-inspired computing paradigm based on oscillatory neural networks (ONNs). While ONNs have been widely studied as Ising machines for tackling complex combinatorial optimization problems, this work investigates their feasibility in solving linear algebra problems, specifically the inverse matrix. Grounded in thermodynamic principles, we analytically demonstrate that the linear approximation of the coupled Kuramoto oscillator model leads to the inverse matrix solution. Numerical simulations validate the theoretical framework, and we examine the parameter regimes that computation has the highest accuracy.
title Thermodynamics-Inspired Computing with Oscillatory Neural Networks for Inverse Matrix Computation
topic Machine Learning
Emerging Technologies
url https://arxiv.org/abs/2507.22544