Accurate Derivation and Efficient Implementation of Higher Order Logic Programming in Hopfield Network

Abstract

The complexity that arose naturally is how symbolic knowledge can be represented and dealt effectively within artificial neural networks. This paper describes the implementation of higher order logic programming in Hopfield network by carrying out computer simulation using NetLogo and running the relaxation for several trials and combination of neurons. In Hopfield network, optimization of logical inconsistency is carried out by the network after the connection strengths are defined from the logic program; the network relaxes to neural states which are models (i.e. viable logical interpretations) for the corresponding logic program. A solution of an optimization problem is obtained after the network is relaxed to an equilibrium state. Applications that benefitted on Hopfield network include solving NP-complete optimization problem such as travelling salesman problem; non-linear and discontinuous data in larger field and connections, and it is able to detect all possible interactions between predictor variables such as detect complex nonlinear relationships of dependent and independent variables.