基于CD生产函数及RNN的黑龙江垦区经济增长研究

为研究黑龙江垦区经济增长问题,首先对柯布-道格拉斯(CD)生产函数进行变形,具体将资本与劳动力投入细化到三种产业得到变形的生产函数,同时建立人工神经网络模型对新的生产函数进行模拟。为反映单个产业自身的投资累积效应,进一步引入自反馈环建立递归神经网络(RNN)模型。该模型可确定投资诸要素间关系,同时反映产业本身及产业结构间的内在联系。数值试验证明该变形生产函数及其RNN模型符合实际,且网络结构简单、算法易于实现、模拟及预测精度高,该算法还可广泛用于投资决策、投资产出预测等经济增长问题。

Research of economic growth in Heilongjiang land reclamation area based on CD production function and RNN

For the problem of economic growth,the Cobb-Douglas(CD) production function is deformed by putting the labor and capital input into the three industries,and an artificial neural network(ANN) model was established to simulate the new production function.A self-feedback loop was introduced to create a recurrent neural network(RNN) model which can simulate the accumulation effect of input in each industry.The model could present the economic growth factors,and it can also reflect the highly nonlinear internal relations among industrial structures by simulation of the relations between input elements and total production.Experiments showed that the results given by this model are reliable and the artificial neural network algorithm was easy to realize.The model can be widely applied in economic problems.