Anomaly Explanation

Abstract

With the surge of deep learning and laws aiming at regulating the use of artificial intelligence, providing explanations to algorithms outputs has been a hot topic in the recent years. Most works are devoted to the explanation of classifiers outputs. The explanation of unsupervised machine learning algorithms, like anomaly detection, has received less attention from the XAI community. But this little interest is not imputable to the irrelevance of the topic. In this paper, we demonstrate the importance of anomaly explanation, the areas still needing investigation based upon our previous contributions to the field, and the future directions that will be explored.