activity
20162026
most citedUnmasking Clever Hans Predictors and Assessing What Machines Really Learn

1k citations · 1.2k across the 60 of their papers we have counts for

collaborators
Showing 2023Show all

10 papers · 1 filter

cs.CV2023★ 1 cited

Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations

Maximilian Dreyer, Reduan Achtibat, Wojciech Samek +1

Ensuring both transparency and safety is critical when deploying Deep Neural Networks (DNNs) in high-risk applications, such as medicine. The field of explainable AI (XAI) has prop…

cs.AI2023★ 8 cited

Human-Centered Evaluation of XAI Methods

Karam Dawoud, Wojciech Samek, Peter Eisert +2

In the ever-evolving field of Artificial Intelligence, a critical challenge has been to decipher the decision-making processes within the so-called "black boxes" in deep learning.…

cs.LG2023

Generative Fractional Diffusion Models

Gabriel Nobis, Maximilian Springenberg, Marco Aversa +11

We introduce the first continuous-time score-based generative model that leverages fractional diffusion processes for its underlying dynamics. Although diffusion models have excell…

cs.LG2023★ 1 cited

Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation

Leander Weber, Jim Berend, Moritz Weckbecker +4

Gradient-based optimization has been a cornerstone of machine learning that enabled the vast advances of Artificial Intelligence (AI) development over the past decades. However, th…

cs.LG2023

From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space

Maximilian Dreyer, Frederik Pahde, Christopher J. Anders +2

Deep Neural Networks are prone to learning spurious correlations embedded in the training data, leading to potentially biased predictions. This poses risks when deploying these mod…

cs.SD2023★ 4 cited

XAI-based Comparison of Input Representations for Audio Event Classification

Annika Frommholz, Fabian Seipel, Sebastian Lapuschkin +2

Deep neural networks are a promising tool for Audio Event Classification. In contrast to other data like natural images, there are many sensible and non-obvious representations for…