Deep learning approaches to anomaly detection (AD) have recently improved the state of the art in detection performance on complex data sets, such as large collections of images or text. These results have sparked a Manuscript

A common machine learning task is to discriminate between normal and anomalous data points. In practice, it is not always sufficient to reach high accuracy at this task, one also would like to understand why a given data point has been predicted in a certain way. We present a new principled approach for one-class SVMs that decomposes outlier predictions in terms of input variables. The method first recomposes the one-class model as a neural network with distance functions and min-pooling, and then performs a deep Taylor decomposition (DTD) of the model output. The proposed One-Class DTD is applicable to a number of common distance-based SVM kernels and is able to reliably explain a wide set of data anomalies. Furthermore, it outperforms baselines such as sensitivity analysis, nearest neighbor, or simple edge detection.

A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems, however, the label information is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerful methods exist for extracting the cluster structure in data, they typically do not answer the question why a certain data point has been assigned to a given cluster. We propose a new framework that can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based on the novel insight that clustering models can be rewritten as neural networks-or "neuralized." Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extract novel insights from the analyzed data and representations.

Unsupervised learning is a subfield of machine learning that focuses on learning the structure of data without making use of labels. This implies a different set of learning algorithms than those used for supervised learning, and consequently, also prevents a direct transposition of Explainable AI (XAI) methods from the supervised to the less studied unsupervised setting. In this chapter, we review our recently proposed ‘neuralization-propagation’ (NEON) approach for bringing XAI to workhorses of unsupervised learning such as kernel density estimation and k-means clustering. NEON first converts (without retraining) the unsupervised model into a functionally equivalent neural network so that, in a second step, supervised XAI techniques such as layer-wise relevance propagation (LRP) can be used. The approach is showcased on two application examples: (1) analysis of spending behavior in wholesale customer data and (2) analysis of visual features in industrial and scene images.