期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2016
卷号：84
期号：2
出版社：Journal of Theoretical and Applied
摘要：Research in the artificial neural network has been attracting and most successful technology in recent years. Though the first model of artificial neurons was presented by Warren McCulloch and Walter Pitts in 1943, the new models have been raised even in the recent years. Some of the problems are solved by mathematical analysis but it leaves many queries openly for further developments. Anyway, the study of neurons, their interconnected nodes and their actions as the brains primary building blocks is one of the most important research fields in modern biology. The purpose of this research paper is to provide how to learn the logic behind the architectures, methodologies of artificial neural networks. This study consists of two parts: the first part shows the learning of single layer feed forward neural network (SLFFNN) architecture where as in second part the multi layer feed forward (MLFFNN) back-propagation neural network covers the learning and training of optimization techniques.
