Maximum 2 satisfiability logical rule in restrictive learning environment
Mohd Shareduwan Mohd Kasihmuddin, Mohd. Asyraf Mansor, Saratha Sathasivam · AIP conference proceedings · 2018
In recent years, there have been significant improvements in algorithm for Maximum 2-Satisfiability Problem (MAX-2SAT). This paper studies the limitation of traditional Hopfield neural network in doing MAX-2SAT problem. More precisely, both traditional exhaustive search method (ES) and artificial bee colony (ABC) were proposed in doing MAX-2SAT problem. Both learning method will optimize the learning phase of Hopfield neural network that act as an intelligent system. Since both learning method will eventually complete the learning phase, the efficiency of both methods is difficult to imagine. In this study, both learning method will undergo restricted learning environment during learning phase of Hopfield neural network. The simulation incorporated with ABC and ES will be examined by using Microsoft Visual 2015 C++ Express software. The performance of both searching techniques in doing MAX-2SAT was evaluated based on root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), Schwarz Bayesian Criterion (SBC), Global minima ratio (Zm) and CPU time. The result obtained from the computer simulation demonstrates the effectiveness, acceleration features of artificial bee colony in doing MAX-2SAT in Hopfield neural network.