An optimal representation to Random Maximum k Satisfiability on the Hopfield Neural Network for High order logic(k ≤ 3)

DOI: 10.48129/kjs.11861

Abstract

This paper proposed a new logical rule by incorporating Random maximum kSatsifiability (RAN-MAX-kSAT) in the Hopfield neural network (HNN) as a single network model (RAN-MAX-kSAT-HNN).  The purpose is to combine the optimization capacity of the Hopfield neural network (HNN) for optimal representation to random maximum kSatsifiability (MAX-RANkSAT). The energy function of a Hopfield neural network has been considered as a programming language for dynamics minimization mechanism. Several optimization problems associated with machine learning (ML) and artificial intelligence (AI) have been expressed on the Hopfield neural network(HNN) optimally by modelling the problem into variables to minimize the objective function that corresponds to Lyapunov energy function of the Hopfield neural network(HNN).  The computer simulation has been developed based on RAN-MAX-kSAT-HNN to explore the feasibility of a Hopfield neural network as a neuro-symbolic integration model in carrying out RAN-MAXkSAT logic programming optimally. The proposed model has been compared with the existing models published in the literature in term of Global minimum ratio (zM), Fitness energy landscapes (FEL), Root Means square error (RMSE), R-square and computation time (CPU). The experimental outcomes positively demonstrate that the HNN is effective in undertaking MAXkSAT logic programming by agreeing with the existing models.