paper-with-me

홈 › Papers

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

2025-07-30 · George Tsormpatzoglou, Filip Sabo, Aida Todri-Sanial arxiv

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.

📄 PDF Abstract BibTeX arXiv:2507.22544

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Decomposing Thermodynamic Dissipation of Linear Langevin Systems via Oscillatory Modes and Its Application to Neural Dynamics

2023-12-06 · Daiki Sekizawa, Sosuke Ito, Masafumi Oizumi

Recent developments in stochastic thermodynamics have elucidated various relations between the entropy production rate (thermodynamic dissipation) and the physical limits of information processing in nonequilibrium dynam…

Brain-inspired interpretable reservoir computing with resonant recurrent neural networks

2025-06-20 · Mark A. Kramer

Traditional artificial neural networks consist of nodes with non-oscillatory dynamics. Biological neural networks, on the other hand, consist of oscillatory components embedded in an oscillatory environment. Motivated by…

Classification

Learning Direct and Inverse Transmission Matrices

2019-01-15 · Daniele Ancora, Luca Leuzzi

Linear problems appear in a variety of disciplines and their application for the transmission matrix recovery is one of the most stimulating challenges in biomedical imaging. Its knowledge turns any random media into an …

regression

Lagrange Oscillatory Neural Networks for Constraint Satisfaction and Optimization

2025-05-12 · Corentin Delacour, Bram Haverkort, Filip Sabo, Nadine Azemard 외

Physics-inspired computing paradigms are receiving renewed attention to enhance efficiency in compute-intensive tasks such as artificial intelligence and optimization. Similar to Hopfield neural networks, oscillatory neu…

Combinatorial Optimization

Inverse Covariance and Partial Correlation Matrix Estimation via Joint Partial Regression

2025-02-12 · Samuel Erickson, Tobias Rydén

We present a method for estimating sparse high-dimensional inverse covariance and partial correlation matrices, which exploits the connection between the inverse covariance matrix and linear regression. The method is a t…