Search

Logic programming is a superior language because it operates on a higher level of mathematical or logical reasoning. Logic programming is well-suited in building the artificial intelligence systems. In this paper, we reviewed the performance of the logic programming in Hopfield Neural Network (HNN) and Radial Basis Function Neural Network (RBFNN). Logic programming by using the Embedding method will improve the performance of RBFNN. In HNN, the logic programming can be implemented by finding the optimal synaptic weight via Wan Abdullah method. RBFNN is expected to do logic programming optimally compared to HNN. This study gives an overview of HNN and RBFNN regarding architectures, learning processing, and their application in 2 Satisfiability (2SAT) logic programming. Both networks will be assessed based on accuracy, sensitivity, and robustness. Pursuing that, RBFNN is expected to outperform HNN in doing 2 Satisfiability logic programming. [ABSTRACT FROM AUTHOR]

A linear Kernel is a machine computationally efficient, also it has the ability to work by the analysis-data in the high-dimensional feature space with complex structure random. The purpose for the study in this paper is to introduce a new vision into the linear kernel machines by integrated with Hopfield Neural Network for doing the logical programming by using horn clause logic to become new network called Linear Kernel Hopfield Neural Network (LKHNN). The benefit by integrating kernel machine with Hopfield network to reduce the arithmetic burden by intelligently determining the pattern of memory embedded in high-dimensional space feature. The new network (LKHNN) able to formulation estimates for the state of neurons. The LKHNN and HNN simulation are performed using Dev C ++ program. The outcomes from simulator show the effectiveness of LKHNN in doing logic program by optimization horn clauses problem and improve efficiency to find the global solution. The robustness of LKHNN and HNN in doing logic programming by using horn clause are evaluated based on global minima ratio(zM), Hamming distance(HD) and computational time(CT). [ABSTRACT FROM AUTHOR]

This paper presents a new framework for the development of generalized composite kernels machines for discrete Hopfield neural network and to upgrading the performance of logic programming in Hopfield network by applying kernels machines in the system. We put up a new family of generalized composite kernels which exhibit great flexibility when combining the spectral and the spatial information contained in the analyze data that make use of kernels. The present an analysis based on kernels machines (Linear kernel Hopfield neural network, Polynomial kernel Hopfield neural network, and Gaussian kernel Hopfield neural network) that measure how the capacity of Hopfield network to use for solving the combinatorial problem that always occurs in Hopfield network and guaranty that the solution is optimal. This work is merely focusing on the ways to upgrade the performance of logic programming in Hopfield network. We carried out computer simulations to demonstrate the ability of kernels Hopfield neural network in enhancing the performance of the system. By applying kernels Hopfield neural network in the system, it does not only produce better quality solutions but it also can handle the network better even though the complexity increased. Besides that, the system also makes the solutions converge faster. Thus, the presence of this kernels Hopfield neural network in the system will produce solutions with better quality [ABSTRACT FROM AUTHOR]