arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09551astro-ph.GAastro-ph.HEastro-ph.IM
收藏

用显著图解释自动AGN分类器

Interpreting automatic AGN classifiers with saliency maps

T. Peruzzi, M. Pasquato, S. Ciroi, M. Berton, P. Marziani, E. Nardini

摘要:

将活动星系核(AGN)的光谱分为不同类型是基于AGN物理学的,但它涉及一定程度的人为疏忽,并且不能可靠地扩展到大数据集。机器学习(ML)以快速和可重复的方式解决了这样的分类问题,但通常被视为黑箱。然而,机器学习的可解释性和可解释性是计算机科学中活跃的研究领域,为我们提供了越来越多的工具来缓解这个问题。我们将ML可解释性工具应用于训练用于从光谱预测AGN类型的分类器,以演示在此背景下使用此类工具。我们在SDSS DR 15的3346个高质量,低红移AGN光谱上训练了一个支持向量机,现有的可靠分类为1型,2型或中间型。在选择的测试集光谱上,我们计算了预测类概率的梯度,并构建了显着性图。我们还可视化的高维空间的活动星系核光谱使用t-分布的随机邻居嵌入(t-SNE),显示我们计算的显着性图的光谱的位置。影响活动星系核类型的区域通常与物理上相关的特征相吻合,例如谱线。t-SNE可视化显示了类型1和类型2光谱的良好可分离性,而中间型光谱如预期的那样位于中间或与类型2光谱混合。显着性图显示了为什么我们的分类器预测了给定的活动星系核类型,从而对影响其决策的光谱区域进行了物理解释,使其不再是一个黑匣子。这些区域与人类专家使用的区域(例如相关谱线)一致,甚至以类似的方式使用,分类器例如通过对线的中心和尾部进行相反的加权来有效地测量线的宽度。

英文摘要:

The classification of the optical spectra of active galactic nuclei (AGN) into different types is well founded on AGN physics, but it involves some degree of human oversight and cannot be reliably scaled to large data sets. Machine learning (ML) tackles such a classification problem in a fast and reproducible way, but is often perceived as a black box. However, ML interpretability and explainability are active research areas in computer science, increasingly providing us with tools to alleviate this issue. We applied ML interpretability tools to a classifier trained to predict AGN type from spectra, to demonstrate the use of such tools in this context. We trained a support-vector machine on 3346 high-quality, low redshift AGN spectra from SDSS DR15 with an existing reliable classification as type 1, type 2, or intermediate type. On a selection of test-set spectra, we computed the gradient of the predicted class probability and we built saliency maps. We also visualized the high-dimensional space of AGN spectra using t-distributed stochastic neighbor embedding (t-SNE), showing where the spectra for which we computed a saliency map are located. Regions that affect the predicted AGN type often coincide with physically relevant features, such as spectral lines. t-SNE visualization shows good separability of type 1 and type 2 spectra, while intermediate-type spectra either lie in-between as expected or appear mixed with type 2 spectra. Saliency maps show why a given AGN type was predicted by our classifier, resulting in a physical interpretation in terms of regions of the spectrum that affected its decision, making it no longer a black box. These regions coincide with those used by human experts such as relevant spectral lines, and are even used in a similar way, with the classifier e.g. effectively measuring the width of a line by weighing its center and its tails oppositely.

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。

↑