An alternative approach to neural network training based on hybrid bio meta-heuristic algorithm

Abstract

Metaheuristic algorithms are popular techniques used to solve several optimization problems. Among the key algorithms, cuckoo search (CS) is a comparatively novel and promising metaheuristic algorithm. Various researchers have shown that it performs better when compared to other metaheuristic algorithms while searching for optimal value and is being used to solve various real-world problems. However, the basic CS algorithm can be improved by enhancing the probabilities of survival of the eggs. It will decrease the possibility of the eggs getting ruined by the host bird. The cuckoo birds move to a new position looking for more search space to get better solutions. Furthermore, better search space can be obtained by executing levy flight with accelerated particle swarm optimization (APSO). This research proposes a new method known as hybrid accelerated cuckoo particle swarm optimization (HACPSO) algorithm, based on two metaheuristic algorithms. In the proposed HACPSO algorithm, APSO provides communication for looking better place having the best nest with greater survivability for cuckoo birds. Different simulation has been carried using standard dataset and efficiency of the proposed algorithm is compared with CS, artificial bee colony and other similar hybrid variants. The simulation results demonstrate that the HACPSO algorithm performs better as compared to other algorithms in term of accuracy, MSE, SD, and with fast convergence rate to the target space.