The establishment of AHP-BP neural network model and its application

The traditional BP neural network is widely used in pattern recognition, image processing and intelligent control, and achieve satisfactory results. However the network has its inherent deficiencies. When we research complex system, for instance, society and economic system, the input variables of the neural network are hard to determine. In the paper, aiming at the characteristics of neural network structure, an idea of connecting AHP and BP is presented. The idea is to use the character that AHP can select the independent variables that affect the dependent variables essentially, and to decide the input variables of BP neural network. Moreover, we adopt this idea to build the AHP-BP neural network model, and design the arithmetic. The AHP-BP neural network model can not only make the selection of input variables easily, but also accelerate the convergence and improve the adaptability of the network. Then we put it use into the economic fields, the results show that this method is superior to the statistical modeling approach.