Black box models only provide results for deep learning tasks and lack informative details about how these results were obtained. In this paper, we propose a general theory that defines a variance tolerance factor (VTF) to interpret the neural networks by ranking the importance of features and constructing a novel architecture consisting of a base model and feature model to demonstrate its utility. Two feature importance ranking methods and a feature selection method based on the VTF are created. A thorough evaluation on synthetic, benchmark, and real datasets is provided.
翻译:黑盒模型只能为深层学习任务提供结果,并且缺乏关于如何取得这些结果的信息细节。在本文件中,我们提出一个一般性理论,界定一个差异容忍系数(VTF)来解释神经网络,方法是对特征的重要性进行排序,并建立一个由基本模型和特征模型组成的新结构,以证明其效用。建立了两个具有特别重要性的排序方法和基于VTF的特征选择方法。提供了对合成、基准和真实数据集的全面评估。