A socio-inspired hybrid election algorithm for random k satisfiability in discrete Hopfield neural network

Metaheuristics and Hopfield neural networks (HNN) are frequently employed to address complex optimization problems. In particular, the iterative and robust metaheuristics technique such as the Election algorithm (EA) is frequently used to dynamically enhance the training phase and converging of the neural network. In this research, we suggest using a recently developed Hybrid Election Algorithm (HEA) in conjunction with Discrete Hopfield Neural Network (DHNN) to solve problems of varying degrees of complexity in Boolean satisfiability programming. Because of its robust operator set, the HEA can be utilised to ease the computational load of DHNN. The primary objective is to enhance the training phase of DHNN such that it optimally represents higher-order logic in terms of Random k Satisfiability. To win over voters, political parties have advocated for a HEA that would allow them to have greater control over areas outside their borders. This strategy is crucial for accelerating the learning of DHNN. Different numbers of neurons (NN) invalidated the robustness and efficiency of HEA in DHNN for RANkSAT logical expressions. Different statistical error accumulations, global minimum solutions, and similarity analysis were used to compare the proposed model against a preexisting EA model during the training phase. The results indicated that the proposed DHNNRANkSAT-HEA model was superior to the previously used DHNNRANkSAT-EA model.