NEURAL NETWORK TRAINING USING HYBRID PARTICLEMOVE ARTIFICIAL BEE COLONY ALGORITHM FOR PATTERN CLASSIFICATION

Abstract

The Artificial Neural Networks Training (ANNT) process is an optimization problem of the weight set which has inspired researchers for a long time. By optimizing the training of the neural networks using optimal weight set, better results can be obtained by the neural networks. Traditional neural networks algorithms such as Back Propagation (BP) were used for ANNT, but they have some drawbacks such as computational complexity and getting trapped in the local minima. Therefore, evolutionary algorithms like the Swarm Intelligence (SI) algorithms have been employed in ANNT to overcome such issues. Artificial Bees Colony (ABC) optimization algorithm is one of the competitive algorithms in the SI algorithms group. However, hybrid algorithms are also a fundamental concern in the optimization field, which aim to cumulate the advantages of different algorithms into one algorithm. In this work, we aimed to highlight the performance of the Hybrid Particle-move Artificial Bee Colony (HPABC) algorithm by applying it on the ANNT application. The performance of the HPABC algorithm was investigated on four benchmark pattern-classification datasets and the results were compared with other algorithms. The results obtained illustrate that HPABC algorithm can efficiently be used for ANNT. HPABC outperformed the original ABC and PSO as well as other state-of-art and hybrid algorithms in terms of time, function evaluation number and recognition accuracy.