A Single-Layer Asymmetric RNN: Potential Low Hardware Complexity Linear Equation Solver

TL;DR

This paper introduces a single-layer asymmetric Hopfield neural network designed to solve linear equations, demonstrating its effectiveness through simulations and experimental results, potentially reducing hardware complexity.

Contribution

It presents a novel asymmetric Hopfield neural network architecture for linear equation solving, expanding the traditional symmetric model with verified simulation and experimental validation.

Findings

Successfully solves linear equations with the asymmetric network

Simulation results verify theoretical predictions

Experimental circuits confirm practical operation

Abstract

A single layer neural network for the solution of linear equations is presented. The proposed circuit is based on the standard Hopfield model albeit with the added flexibility that the interconnection weight matrix need not be symmetric. This results in an asymmetric Hopfield neural network capable of solving linear equations. PSPICE simulation results are given which verify the theoretical predictions. Experimental results for circuits set up to solve small problems further confirm the operation of the proposed circuit.