This article tackles two major problem settings for interpretability of audio processing
networks, post-hoc and by-design interpretation. For post-hoc interpretation, we aim to …

Discovering patterns in data that best describe the differences between classes allows to
hypothesize and reason about class-specific mechanisms. In molecular biology, for …

Recent advances in Artificial Intelligence (AI) especially in deep learning have manifested
an increasing concern in trustworthiness, and its subparts such as interpretability, safety …

Abstract Non-markovian Reinforcement Learning (RL) tasks are extremely hard to solve,
because intelligent agents must consider the entire history of state-action pairs to act …

Abstract Non-markovian Reinforcement Learning (RL) tasks are very hard to solve, because
agents must consider the entire history of state-action pairs to act rationally in the …

In this work, we introduce DeepDFA, a novel approach to identifying Deterministic Finite
Automata (DFAs) from traces, harnessing a differentiable yet discrete model. Inspired by …

Pattern mining addresses the challenge of automatically identifying interpretable and
discriminative patterns within data. Recent approaches, leveraging differentiable approach …

We consider rule induction as a valuable tool in developing automated business decision
services. For this use case, we present first results towards a comprehensive benchmark of …

Discovering patterns for classification of sequential data is of key importance for a variety of
fields, ranging from genomics to fraud detection. In this short paper, we propose a …

Explainable AI seeks to unveil the intricacies of black box models through post-hoc
strategies or self-interpretable models. In this paper, we tackle the problem of building layers …