首页|Study Results from Chulalongkorn University Broaden Understanding of Machine Lea rning (An Efficient Lightgbm-based Differential Evolution Method for Nonlinear I nelastic Truss Optimization)
Study Results from Chulalongkorn University Broaden Understanding of Machine Lea rning (An Efficient Lightgbm-based Differential Evolution Method for Nonlinear I nelastic Truss Optimization)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning. According to news reporting originating from Bangkok, Thailand, by Ne wsRx correspondents, research stated, "A metaheuristic-based structural optimiza tion method, whilst being popularly adopted due to its advantages in by-passing gradient function calculations, requires the use of time-consuming advanced anal yses for constraint evaluation. To overcome this drawback, the present paper pro poses a robust (machine learning-based) optimization method that combines the li ght gradient boosting machine (LightGBM) with the efficient p-best differential evolution (EpDE) method." Financial supporters for this research include Thailand Science Research and Inn ovation Fund Chulalongkorn University, Ratchadapisek Somphot Fund for Postdoctor al Fellowship, Chulalongkorn University. Our news editors obtained a quote from the research from Chulalongkorn Universit y, "In essence, the LightGBM classification model is constructed to assess the c onstraint (safety and integrity) satisfaction of structures. An efficient framew ork using a so-called safety parameter is proposed to prevent inaccurate predict ions of the LightGBM model. The EpDE processes the optimization procedures on th e constructed classification LightGBM model. This enables an enhanced machine le arning-based optimization technique that not only maintains the sufficiently acc urate optimal design of structures but also significantly reduces the required c omputing efforts, as compared to standard optimization schemes. Various examples of steel structure designs (i.e., two of which have been provided herein) have been successfully performed by the proposed approach. These illustrate the accur acy and robustness of the proposed method, where good comparisons with reference algorithms (including standard DE with ‘DE/rand/1' mutational strategy, Jaya, R ao-1 and CaDE) are evidenced."
NETL
NSTL
