期刊
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
卷 25, 期 1, 页码 121-129出版社
SPRINGER
DOI: 10.1007/s11831-017-9237-0
关键词
-
类别
资金
- NRF (National Research Foundation of Korea) - MEST (Ministry of Education and Science Technology) of Korean government [NRF-2017R1A4A1015660]
Since the first journal article on structural engineering applications of neural networks (NN) was published, there have been a large number of articles about structural analysis and design problems using machine learning techniques. However, due to a fundamental limitation of traditional methods, attempts to apply artificial NN concept to structural analysis problems have been reduced significantly over the last decade. Recent advances in deep learning techniques can provide a more suitable solution to those problems. In this study, versatile background information, such as alleviating overfitting methods with hyper-parameters, is presented. A well-known ten bar truss example is presented to show condition for neural networks, and role of hyper-parameters in the structures.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据