Portal de Periódicos da CAPES

Accelerating Activation Function for 3- Satisfiability Logic Programming

2016; Volume: 8; Issue: 10 Linguagem: Inglês

10.5815/ijisa.2016.10.05

2074-9058

Mohd. Asyraf Mansor, Saratha Sathasivam,

Rough Sets and Fuzzy Logic

This paper presents the technique for accelerating 3-Sat isfiability (3-SAT) logic programming in Hopfield neural network.The core impetus for this work is to integrate activation function for doing 3-SAT logic programming in Hopfield neural network as a single hybrid network.In logic programming, the activation function can be used as a dynamic post optimizat ion paradigm to transform the activation level of a unit (neuron) into an output signal.In this paper, we proposed Hyperbolic tangent activation function and Elliot symmetric activation function.Next, we co mpare the performance of p roposed activation functions with a conventional function, namely McCu lloch-Pitts function.In this study, we evaluate the performances between these functions through computer simu lations.Microsoft Visual C++ 2013 was used as a platform for training, validating and testing of the network.We restrict our analysis to 3-Satisfiab ility (3-SAT) clauses.Moreover, evaluations are made between these activation functions to see the robustness via aspects of global solutions, global Hamming distance, and CPU time.