Jacob R. Kauffmann

TL;DR: This review aims to identify the common underlying principles and the assumptions that are often made implicitly by various methods in deep learning, and draws connections between classic “shallow” and novel deep approaches and shows how this relation might cross-fertilize or extend both directions.

TL;DR: 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 as mentioned in this paper, and led to the introduction of a great variety of new methods.

TL;DR: In this paper, the authors propose a principled approach for one-class SVMs (OC-SVM) that can be rewritten as distance/pooling neural networks, and 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.

TL;DR: A new framework is proposed that can, for the first time, explain cluster assignments in terms of input features in a comprehensive manner, based on the novel theoretical insight that clustering models can be rewritten as neural networks, or 'neuralized'.

TL;DR: An explainable AI (XAI) procedure that can highlight the relevant features used by popular anomaly detection models of different type and points at a possible way out of the Clever Hans dilemma by allowing multiple anomaly models to mutually cancel their individual structural weaknesses to jointly produce a better and more trustworthy anomaly detector.