论文标题
识别$ h \ rightarrow b \ bar {b} $ jets的交互网络的解释性
Interpretability of an Interaction Network for identifying $H \rightarrow b\bar{b}$ jets
论文作者
论文摘要
多年来，多元技术和机器学习模型在高能量物理（HEP）研究中发现了许多应用。最近，基于深神网络的AI模型在许多这些应用中越来越流行。但是，神经网络被认为是黑匣子 - 由于它们的高度复杂性，通常很难通过建立可拖动的输入输出关系和通过深层网络层的信息传播来定量地解释神经网络的输出。随着近年来可解释的AI（XAI）方法越来越流行，我们通过检查旨在识别旨在识别$ h \ bar {b} $ jets的增强的$ h \ jets的相互作用网络（IN）模型来探索AI模型的解释性。我们探讨了不同的定量方法，以证明分类器网络如何基于输入以及如何利用此信息来重新启动模型制作，从而更简单但同样有效。我们还将模型中隐藏层的活性描述为神经激活模式（NAP）图。我们的实验表明，小睡图揭示了有关如何在深层模型的隐藏层中传达信息的重要信息。这些见解对于有效的模型重新优化和高参数调整可能是有用的。
Multivariate techniques and machine learning models have found numerous applications in High Energy Physics (HEP) research over many years. In recent times, AI models based on deep neural networks are becoming increasingly popular for many of these applications. However, neural networks are regarded as black boxes -- because of their high degree of complexity it is often quite difficult to quantitatively explain the output of a neural network by establishing a tractable input-output relationship and information propagation through the deep network layers. As explainable AI (xAI) methods are becoming more popular in recent years, we explore interpretability of AI models by examining an Interaction Network (IN) model designed to identify boosted $H\to b\bar{b}$ jets amid QCD background. We explore different quantitative methods to demonstrate how the classifier network makes its decision based on the inputs and how this information can be harnessed to reoptimize the model-making it simpler yet equally effective. We additionally illustrate the activity of hidden layers within the IN model as Neural Activation Pattern (NAP) diagrams. Our experiments suggest NAP diagrams reveal important information about how information is conveyed across the hidden layers of deep model. These insights can be useful to effective model reoptimization and hyperparameter tuning.
