作　　者： ; ; ;

机构地区： 佛山科学技术学院

出　　处： 《工业建筑》 2007年第z1期973-974,1003,共3页

摘　　要： 以往对神经网络预测结果的评价常采用相对误差方法。对于有随机因素影响的样本数据,该方法已经不再适用。对此进行了深入研究,以数理统计理论为基础,提出了适合随机问题的评价方法。土木工程实际应用结果表明,该方法是可行的,评价结论更贴近工程实际。 In the past,the predicted results produced by neural network models were often evaluated by using the relative error.But it is no longer fitted for random training samples.Therefore,based on mathematics statistics theory,this thesis presents a new evaluation method for random training samples.When applied to civil engineering,experimental results justify that this evaluation method is useful,and its conclusion is close to engineering actualities.

关 键 词： 神经网络 结果评价 统计学 随机性

领　　域： [建筑科学]