Ant colony optimization for 2 satisfiability in restricted neural symbolic integration

Abstract

2 Satisfiability (2SAT) is a language that bridges real life application to neural network optimization. 2SAT is an interesting paradigm because the outcome of this logical rule is always positive. Hopfield Neural Network (HNN) is a type of neural network that finds the solution based on energy minimization. Interesting intelligent behavior has been observed when logical rule is embedded to HNN. Increasing the storage capacity during learning phase of HNN has been a challenging problem for most neural network researchers. Ant Colony Optimization (ACO) is a population-based and nature-inspired algorithm to decipher several combinatorial optimization problems. In this paper, metaheuristic algorithm ACO will be proposed in learning 2SAT programming. To this end, all the learning model will be tested in a new restricted learning environment. In circumstances of where HNN model was not given unlimited iteration until all 2SAT clauses were fully satisfied, we would like to determine the better performing search method between exhaustive search and ACO. Results acquired from the computer simulation showed that ACO outperformed exhaustive search in restricted learning environment.