基于BP神经网络的模型结构自动选择

Model Selection Based on BP Neural Network

模型选择方法对用户的期望过高,要求用户对决策支持系统模型库中的模型和所要解决的问题都要有深刻的理解,这就导致了模型选择的实用性较差,在论述BP神经网络及算法的基础上,将其应用于模型结构的自动选择,并利用Matlab仿真软件进行了验证,试验结果表明此方法是有效的。

Model selection is an important component of model management system of decision support systems （DSS）. A crucial problem confronting users of DSS is that the present methods of model selection require the users too much. The users are required to have a profound understanding of the models in the model base and the problems to be solved. This leads to poor feasibility of model selection. BP network has applied in model selection after BP network and has been discussed, and he result is calculated and analyzed by using Matlab simulation software, the result shows： the method is effective.