Kernel Machine to Doing Logic Programming In Hopfield Network for Solve Non Horn Problem-3SAT

Abstract

Kernel machine is computationally efficient and has the capability to function on high dimensional analysis data with random complex structure. The aim of this research is to provide a new insight on the kernel machines integrated with Hopfield Network in doing logic programming (KHNN). The newly proposed method emphasized on non horn clauses logic. Kernel machine reduced the computational burden by intelligently define the embedded memory pattern in high dimensional feature space. Since KHNN is able to formulate the estimation of neuron states efficiently, computation in high dimensional feature space of the network can be reducing dramatically. The simulation of KHNN will be executed by using Dev C++ software. The robustness of KHNN in doing non horn clause 3 sat will be evaluated based on global minima ratio, root mean square error (RMSE), and sum of squared error (SSE), mean absolute error (MAE), mean percentage error (MAPE) and computation time. The result obtained from the computer simulation demonstrates the effectiveness of KHNN in doing non horn clause problem-3 sat.