An optimal representation to random maximum k satisfiability on the hopfield neural network for high order logic(k ≤3)‎

Abstract EN

This paper proposes a new logical rule by incorporating Random Maximum k Satsifiability in the Hop field neural network as a single model.

The purpose is to combine the optimization capacity of the Hopfield neural network with non-systematic behaviour of the Random maximum k Satisfiability for classification problem.

The energy function of a Hopfield neural network has been considered as a pro gramming language for dynamics minimization mechanism.

Several optimization and search problems associated with machine learning (ML), decision science (DS) 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 corresponding to Lyapunov energy function of the model.

The com puter simulation has been developed based on RANMAXKSAT logical rule in exploring the feasibility of the Hopfield neural network as a neuro-symbolic integration model for optimal classification prob lems.

The perfromanmce of the proposed hybrid 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), Mean absolute errors and computation time (CPU).

Hence, based on the experimental simulation results, it revealed that the RANMAXKSAT can optimally and effectively be represented in the Hopfield neural network (HNN) with 85.1 % classification accuracy.