Hybrid Genetic Algorithm Model in Neuro Symbolic Integration

Shehab Abdulhabib Alzaeemi ,Saratha Sathasivam ,Muraly Velavan

doi:10.35940/ijeat.d8761.049420

Abstract

The development of artificial neural network and logic programming plays an important part in neural network studies. Genetic Algorithm (GA) is one of the escorted randomly searching technicality that uses evolutional concepts of the natural election as a stimulus to solve the computational problems. The essential purposes behind the studies of the evolutional system is for developing adaptive search techniques which are robust. In this paper, GA is merged with agent based modeling (ABM) by using specified proceedings to optimise the states of neurons and energy function in the Hopfield neural network (HNN). Hence, it is observed that the GA provides the best solutions in affirming optimal states of neurons and thus, enhancing the performance of Horn Satisfiability logical program (HornSAT) in Hopfield neural network. This is due to the fact that the GA lesser susceptive to be restricted in the local optimal or in any suboptimal solutions. NETLOGO version 6.0 will be used as a dynamic platform to test our proposed model. Hence, the computer simulations will be carried out to substantiate and authenticate the efficiency of the proposed model. The results are then tabulated by evaluating the global minimum ratio, computational time and hamming distance

Highlights

The biological and performance structure of the neural network has inspired new models to compute performing tasks for the recognition of patterns type problems
The operation of biological neurons and the neural interconnection aren't completely understood until this extremely days [1].One of the customary neural networks is the Hopfield Neural Network (HNN), that was launched by John Hopfield
HNN is the recurrent neural network prominent to outstand powerful in storage, memory, and learning [2]

Summary

Introduction

The biological and performance structure of the neural network has inspired new models to compute performing tasks for the recognition of patterns type problems. Those computing models aren't expecting for reaching the best levels of biological networks because of numerous reasons. HNN is the recurrent neural network prominent to outstand powerful in storage, memory, and learning [2].

Methods

Results

Conclusion