arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.00433physics.data-anhep-exhep-ph
收藏

生成对抗网络的展开

Unfolding with Generative Adversarial Networks

Kaustuv Datta, Deepak Kar, Debarati Roy

摘要:

将测量的探测器水平分布校正到粒子水平是使数据在实验合作之外可用的关键。术语展开用于描述该过程。本文提出了一种使用改进的生成对抗网络(MSGAN)展开数据的新方法。应用于各种分布的广泛不同的形状,它的表现大致与目前使用的方法。这是一个最先进的机器学习方法的原理证明,可以用来很好地模拟检测器的影响。

英文摘要:

Correcting measured detector-level distributions to particle-level is essential to make data usable outside the experimental collaborations. The term unfolding is used to describe this procedure. A new method of unfolding data using a modified Generative Adversarial Network (MSGAN) is presented here. Applied to various distributions with widely different shapes, it performs roughly at par with currently used methods. This is a proof-of-principle demonstration of a state-of-the-art machine learning method that can be used to model detector effects well.

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。

↑