A Single-Layer Asymmetric RNN: Potential Low Hardware Complexity Linear Equation Solver
This work addresses the need for low hardware complexity linear equation solvers, but it appears incremental as it modifies the standard Hopfield model by allowing asymmetry.
The authors tackled the problem of solving linear equations by proposing a single-layer asymmetric Hopfield neural network, which was verified through PSPICE simulations and experimental results on small problems.
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.