Abstract Detecting anomalies in the data is a common machine learning task, with numerous applications in the sciences and industry. In practice, it is not always sufficient to reach high detection accuracy, one would also like to be able to understand why a given data point has been predicted to be anomalous. We propose a principled approach for one-class SVMs (OC-SVM), that draws on the novel insight that these models can be rewritten as distance/pooling neural networks. This ‘neuralization’ step lets us apply deep Taylor decomposition (DTD), a methodology that leverages the model structure in order to quickly and reliably explain decisions in terms of input features. The proposed method (called ‘OC-DTD’) is applicable to a number of common distance-based kernel functions, and it outperforms baselines such as sensitivity analysis, distance to nearest neighbor, or edge detection.

中文翻译：

---

解释异常：一类模型的深度泰勒分解

摘要 检测数据中的异常是一项常见的机器学习任务，在科学和工业中有许多应用。在实践中，达到高检测精度并不总是足够的，人们还希望能够理解为什么给定的数据点被预测为异常。我们为一类 SVM (OC-SVM) 提出了一种有原则的方法，它利用了这些模型可以重写为距离/池化神经网络的新见解。这个“神经化”步骤让我们可以应用深度泰勒分解 (DTD)，这是一种利用模型结构的方法，以便根据输入特征快速可靠地解释决策。所提出的方法（称为“OC-DTD”）适用于许多常见的基于距离的核函数，它优于基线，如敏感性分析，