The effect of two-term parameters on the performance of third-order neural network on medical classification problems

Abstract

Artificial neural networks (ANN) also known as backpropagation (BP) algorithm has recently been applied in many areas and applications. BP algorithm is known as an excellent classifier for nonlinear input and output numerical data. However, the popularity of BP comes with some weaknesses which are moderate in learning and easily getting stuck in local minima. A vigorous area of research and papers on enlightening the performance of BP algorithm are revised especially in terms of literature. Furthermore, the performance of BP algorithm also highly influenced by the order of learning and the parameters that been chosen. This paper presents an improvement of BP algorithm by adjusting the two-term parameters on the performance of third-order neural network methods. The effectiveness of the proposed method is proven through the methods of stimulation on medical classification issues. The results show that the proposed implementation significantly improves the learning speed of the general BP algorithm.