论文标题
计算中级输入功能相关性的一般方法
A general approach to compute the relevance of middle-level input features
论文作者
论文摘要
这项工作在可解释的人工智能（XAI）的背景下提出了一个新颖的通用框架，以根据中级特征来构建机器学习（ML）模型行为的解释。一个人可以隔离两种不同的方式来在XAI的背景下提供解释：低和中层的解释。引入了中层解释，以减轻一些低级解释的缺陷，例如在图像分类的背景下，人类用户承担着重大的解释性负担：从低级解释开始，必须从低级解释开始，人们必须确定对人类视觉系统的整体投入的属性。但是，在文献中从未提出过正确评估ML模型反应的中级解释要素的一般方法。
This work proposes a novel general framework, in the context of eXplainable Artificial Intelligence (XAI), to construct explanations for the behaviour of Machine Learning (ML) models in terms of middle-level features. One can isolate two different ways to provide explanations in the context of XAI: low and middle-level explanations. Middle-level explanations have been introduced for alleviating some deficiencies of low-level explanations such as, in the context of image classification, the fact that human users are left with a significant interpretive burden: starting from low-level explanations, one has to identify properties of the overall input that are perceptually salient for the human visual system. However, a general approach to correctly evaluate the elements of middle-level explanations with respect ML model responses has never been proposed in the literature.
