IMPROVED CUCKOO SEARCH ALGORITHM FOR FEEDFORWARD NEURAL NETWORK TRAINING

The cuckoo search algorithm is a recently developed meta-heuristic optimization algorithm, which issuitable for solving optimization problems. To enhance the accuracy and convergence rate of thisalgorithm, an improved cuckoo search algorithm is proposed in this paper. Normally, the parameters ofthe cuckoo search are kept constant. This may lead to decreasing the efficiency of the algorithm. To copewith this issue, a proper strategy for tuning the cuckoo search parameters is presented. Then, it isemployed for training feedforward neural networks for two benchmark classification problems. Finally, the performance of the proposed algorithm is compared with that of the standard cuckoo search. Simulation results demonstrate the effectiveness of the proposed algorithm