利用BP人工神经网络方法对人口按龄生育率问题进行建模和仿真,得到了较为理想的拟合结果。这一结果表明使用人工神经网络方法模拟生育率结构动态具有建模简单和拟合精度高的特点,在降低模型复杂性上优于传统方法。

[1] Jun Zhu.A model of the age patterns of births by parity in natural fertility populations.Mathematical population studies.1994,2:153-173
[2] Henry,Louis.Theoretical basis of measures of natural fertility.On the Measurement of Human Fertility.New York:Elsevier,1953
[3] Coale,A.J.,and McNeil,D.R.The distribution by age at first marriage in a female cohort.Journal of the American Statistcal Association 67(340):743-749,1972
[4] Cybenko G.Approximations by Superpositions of sigmoidal Function.Mathematics of control.Signals and Systems.1989(2):303-314
[5] Fanahashi K.On the Approximate Realization of Continuous Mapping by Neural Networks.Neural Networks.1989,2:183-192
[6] J-N.Hwang,M.Maechler.Regression modeling in back-propagation and projection pursuit learning.IEEE transactions on neural networks,Vol.5,No.3,May 1994:343-353
[7] Weigend A S,Rumeihart D E,Huberman B A.Back-propagation,weightelimination and time seris prediction.In:Proceedings of the Connectionist Models,1990,105-116。