arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.11005math.OC
收藏

设计中的机器学习算法Optimization

Machine Learning Algorithms in Design Optimization

Daniele Peri

摘要:

复杂系统的数值优化得益于近二十年来计算平台技术的发展。不幸的是,这仍然是不够的,并且当采用包括更丰富(因此更真实)的物理模型的数学模型时,仍然需要大量的计算时间。在本文中,我们展示了优化和人工智能(AI)的结合,特别是机器学习算法,可以帮助大大减少整体计算时间,使优化周期内使用复杂的仿真系统成为可能。还提出了一些新的方法。

英文摘要:

Numerical optimization of complex systems benefits from the technological development of computing platforms in the last twenty years. Unfortunately, this is still not enough, and a large computational time is still necessary when mathematical models that include richer (and therefore more realistic) physical models are adopted. In this paper we show how the combination of optimization and Artificial Intelligence (AI), in particular the Machine Learning algorithms, can help in strongly reducing the overall computational times, making possible the use of complex simulation systems within the optimization cycle. Original approaches are also proposed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑