arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.08005cs.NEcs.LGstat.ML
收藏

基于约束遗传编程的实验物理一致性特征构造

Consistent Feature Construction with Constrained Genetic Programming for Experimental Physics

CEA, LIST(法国原子能与替代能源委员会 信息技术与系统实验室);Irfu, CEA, Université Paris-Saclay(巴黎萨克雷大学 法国原子能与替代能源委员会 核物理与粒子物理研究所)

Noëlie Cherrier, Jean-Philippe Poli, Maxime Defurne, Franck Sabatié

摘要:

良好的特征表示是许多机器学习算法在分类方面实现高性能的决定性因素。这对于不构建复杂的数据内部表示的技术(例如,与深度神经网络相反的决策树)尤其如此。为了变换特征空间,特征构造技术从原始特征构造新的高级特征。在这些技术中,遗传编程是一个很好的候选人,提供高能物理数据分析所需的可解释的功能。传统上,原始特征或基于物理学第一原理的更高级特征被用作训练的输入。然而,物理学家将受益于一个自动和可解释的特征结构,用于粒子碰撞事件的分类。我们的主要贡献在于结合不同方面的遗传编程,并将其应用到实验物理的特征建设。特别地,为了适用于物理学,使用语法来强制维度一致性。在三个物理数据集上的实验结果表明,所构造的特征能显著提高分类精度。据我们所知,这是第一次提出一种方法,用于使用测量单位进行可解释的特征构建,并且高能物理专家验证了整体方法以及构建特征的可解释性。

英文摘要:

A good feature representation is a determinant factor to achieve high performance for many machine learning algorithms in terms of classification. This is especially true for techniques that do not build complex internal representations of data (e.g. decision trees, in contrast to deep neural networks). To transform the feature space, feature construction techniques build new high-level features from the original ones. Among these techniques, Genetic Programming is a good candidate to provide interpretable features required for data analysis in high energy physics. Classically, original features or higher-level features based on physics first principles are used as inputs for training. However, physicists would benefit from an automatic and interpretable feature construction for the classification of particle collision events. Our main contribution consists in combining different aspects of Genetic Programming and applying them to feature construction for experimental physics. In particular, to be applicable to physics, dimensional consistency is enforced using grammars. Results of experiments on three physics datasets show that the constructed features can bring a significant gain to the classification accuracy. To the best of our knowledge, it is the first time a method is proposed for interpretable feature construction with units of measurement, and that experts in high-energy physics validate the overall approach as well as the interpretability of the built features.

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。

↑