ABSTRACT
This chapter presents an enhanced feed-forward neuronet that is a three-layer feed-forward power-activation neuronet equipped with the weights-and-structure-determination (WASD) algorithm, to predict the Chinese population. Undoubtedly, the effectiveness of the measures depends crucially on the accurate prediction of Chinese population. Many methods, including the feed-forward neuronet equipped with back-propagation (BP) algorithm, have been proposed in order to improve the prediction accuracy. The WASD neuronet has two advanced features compared with the conventional BP neuronet. The chapter discusses a three-layer power-activation neuronet model is constructed for the general purpose of Chinese population prediction. Population is one of the most significant factors affecting the social and economic development of a country. Population is an important factor related to the potential of economic growth. The United Nations publishes the prediction of Chinese population every two years in a report. The prediction is based on the standard cohort-component method.
