人工神经网络在综合评价决策中的应用

为了克服综合评价过程的随机性与评价专家主观上的不确定性,文章提出了基于人工神经网络的多目标综合评价方法,并使其应用于企业经济效益的综合评估。该方法采用多层前馈神经网络及BP算法,其仿真实现是以MATLAB下神经网络工具箱作为开发工具,通过仿真实例与专家评估相比较,验证了该方法的有效性。

Application of artificial neural network in decision-making of comprehensive evaluation

This dissertation studies applied problems of artificial neural network in managing decision-making. In order to avoid the random in the process of evaluation and idealistic uncertainty of experts, a method based on ANN for multiobject comprehensive evaluation is proposed, and applied in comprehensive evaluation of corporation economic efficiency. In this method, multilayered feedforward neural network and BP training algorithm are adopted and neural network toolbox based on the software MATLAB is used for emulational realization.Then validity of the method is proved with an example in which emulational evaluation is compared with that of experts.