Saved in:
Bibliographic Details
Main Authors: Shahhosseini, Amir, Burger, Thomas, Sepulchre, Rodolphe
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.06793
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909572733599744
author Shahhosseini, Amir
Burger, Thomas
Sepulchre, Rodolphe
author_facet Shahhosseini, Amir
Burger, Thomas
Sepulchre, Rodolphe
contents This paper proposes a variable metric splitting algorithm to solve the electrical behavior of neuromorphic circuits made of capacitors, memristive elements, and batteries. The gradient property of the memristive elements is exploited to split the current to voltage operator as the sum of the derivative operator, a Riemannian gradient operator, and a nonlinear residual operator that is linearized at each step of the algorithm. The diagonal structure of the three operators makes the variable metric forward-backward splitting algorithm scalable and amenable to the simulation of large-scale neuromorphic circuits.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06793
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Variable Metric Splitting Methods for Neuromorphic Circuits Simulation
Shahhosseini, Amir
Burger, Thomas
Sepulchre, Rodolphe
Systems and Control
This paper proposes a variable metric splitting algorithm to solve the electrical behavior of neuromorphic circuits made of capacitors, memristive elements, and batteries. The gradient property of the memristive elements is exploited to split the current to voltage operator as the sum of the derivative operator, a Riemannian gradient operator, and a nonlinear residual operator that is linearized at each step of the algorithm. The diagonal structure of the three operators makes the variable metric forward-backward splitting algorithm scalable and amenable to the simulation of large-scale neuromorphic circuits.
title Variable Metric Splitting Methods for Neuromorphic Circuits Simulation
topic Systems and Control
url https://arxiv.org/abs/2504.06793