Hybrid ant colony optimization for even-2 satisfiability programming in Hopfield neural network.

Restricted Boolean 2 Satisfiability (2SAT) is a variant of discrete constraint satisfaction problem, commonly being applied with Hopfield neural network (HNN) as logic programming. In recent years, the binary Ant colony optimization has been formulated to solve various satisfaction and optimization problem due to the power onlooker bee phase in attaining the global convergence. The core motivation of this research is to propose a hybrid Hopfield neural network (HNN) incorporated ACO in enhancing the learning phase of new type of 2SAT logic programming. The developed hybrid model will be compared with the other conventional learning method in hybrid HNNs models such as genetic algorithm (GA) and exhaustive search (ES). The simulations were conducted by training and testing the developed model and the other counterparts with randomized simulated data sets. Therefore, the results manifested the capability of ACO in improving the learning phase of HNN as compared with GA and ES under different complexities. [ABSTRACT FROM AUTHOR]