Neural network is a software computational tool applied in many different technological aspects, such as automation and control
electronics and telecommunications
information technology... The success of an artificial neural network depends significantly on network learning process. The result of learning process is affected by two main factors which include network training algorithm and initial weights. This paper investigates the influence of the different initial weights on neural network training results generated by a proposed network training algorithm. The significant impact will clearly be shown when a special error is available in a neural network, for instance, the cleft error surface. Obtained results of this study contribute significantly to the improvement of learning algorithms of neural networks, and especially, in cases of neural networks with an error surface.