Genetic Algorithm in Logic Programming in Neural Network

The development of artificial neural network and logic programming plays an important part in neural network studies. Genetic algorithms (GAs) are one of the guided random search techniques that use evolutionary ideas of natural selection as an inspiration for solving computational problems. The basic idea behind the study of evolutionary systems is to develop a robust and adaptive search technique. GAs can be used as an optimization tool for engineering problems and other real world complex problems. Furthermore, GAs have been widely employed as an optimization technique such as function optimizer, which exploits random search within a defined search space to solve problems. Netlogo version 6.0 will be used as the dynamic platform for training and testing the proposed models. Hence, the computer simulations will be carried out to validate and authenticate the effectiveness on the activation functions on the proposed model. GAs are merged into the developed agent based modelling (ABM) using specific procedures to optimize neuron states and energy in the Hopfield network. The results are then tabulated by evaluating the global minima ratio, computational time and hamming distance of the GAs with the previous method proposed by Wan Abdullah. The results obtained show improvement in global minima ratio, Computational time and harming distance. We assumed that this is due to the fact that GAs is less susceptible to been trapped in local optima or in any sub-optimal solutions. Hence, it is observed that GAs provide better solutions in finding optimal neuron states and thus, enhance the performance of doing logic programming in Hopfield network. Keywords - Genetic Algorithm, Hopfield Network, 3-Satisfiability Problem, Netlogo