对粗集-神经网络理论进行了讨论,在神经网络基础上,提出粗集—神经网络项目评估方法。该方法利用粗糙集理论对数据样本进行数据浓缩,从给定学习样本数据中发现一组规则,提取规则作为神经网络的输入,该方法简化了神经网络的结构,提高训练效率,对我国农业工程项目后评估进行仿真,评价结果是合理的,具有较大的参考价值,在实际中有良好的应用前景。
The theory of rough set-neural network was discussed. A new method for rough set-neural network based on the neural network was proposed, which used rough set theory to enrich data and extract the mapping rules from the sample data as the input of the neural network. A set of rules were found from the given training data by using Rough Set theory .The rough set-neural network based on reduction reduces the dimension of input to neural network, and raises the efficiency of training ,The simulation of post-evaluation for agricultural engineering projects shows that the method is effective and reasonable. It shows their reference values. There will be good application prospect in practice.