A comparative performance analysis between 2-satisfiability and random 3-satisfiability in Discrete Hopfield Neural Network.

Discrete Hopfield Neural Network (DHNN) is very prominent in the study of Artificial Neural Network (ANN). In the DHNN, systematic logic suffers for interpretability and variation. These issues may be overcome by introducing non-systematic logical rules in the structure of DHNN. In this study, we compare the performance of a non-systematic logical rule and a systematic logical rule. Here, we consider one of the non-systematic logical structures named Random 3 Satisfiability (RAN3SAT) with the logical combination of k=2, 3 and the systematic, logical structure called 2 Satisfiability (2SAT). For example, the Exhaustive Search method incorporates the RAN3SAT and 2SAT with DHNN. To compare better, we employ performance measurements with a fixed number of neurons. The expected outcome of our experiment is that RAN3SAT (the non-systematic logical rule) can outperform 2SAT (the systematic logical rule). This finding will create a better phenomenon in the study of logic programming. [ABSTRACT FROM AUTHOR]