Aktuelle Publikationen

Juni 2023

Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations

Maximilian Dreyer, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin, Reduan Achtibat

Applying traditional post-hoc attribution methods to segmentation or object detection predictors offers only limited insights, as the obtained feature attribution maps at input level typically resemble the models' predicted segmentation mask or...

Juni 2023

Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models

Frederick Pahde, Wojciech Samek, Sebastian Lapuschkin, Maximilian Dreyer

State-of-the-art machine learning models often learn spurious correlations embedded in the training data. This poses risks when deploying these models for high-stake decision-making, such as in medical applications like skin cancer detection. To...

Juni 2023

The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus

Anna Hedström, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne, Philine Bommer, Kristoffer K. Wickstrøm

Explainable AI (XAI) is a rapidly evolving field that aims to improve transparency and trustworthiness of AI systems to humans. One of the unsolved challenges in XAI is estimating the performance of these explanation methods for neural networks,...

Juni 2023

Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement

Leander Weber, Wojciech Samek, Alexander Binder, Sebastian Lapuschkin

Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex and opaque machine learning (ML) models. This paper offers a comprehensive overview over techniques that apply XAI practically to...

Juni 2023

Sydnone Methides: Intermediates between Mesoionic Compounds and Mesoionic N-Heterocyclic Olefins

Sebastian Mummel, Eike Hübner, Felix Lederle, Jan C. Namyslo, Martin Nieger, Andreas Schmidt

Sydnone methides represent an almost unknown class of mesoionic compounds which possess exocyclic carbon substituents instead of oxygen (sydnones) or nitrogen (sydnone imines) in the 5-position of a 1,2,3-oxadiazolium ring. Unsubstituted...

Juni 2023

Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models

Daniel Krakowczyk, Sebastian Lapuschkin, David Robert Reich, Paul Prasse, Lena Ann Jäger, Tobias Scheffer

Recent work in XAI for eye tracking data has evaluated the suitability of feature attribution methods to explain the output of deep neural sequence models for the task of oculomotric biometric identification. In this work, we employ established...

Mai 2023

Demonstration of a 15-Mode Network Node Supported by a Field-Deployed 15-Mode Fiber

Ruben S. Luis, A. Mecozzi, Colja Schubert, F. Achten, Robert Emmerich, Nicolas Braig-Christophersen, Georg Rademacher, Hideaki Furukawa, Giammarco Di Sciullo, Andrea Marotta, Ralf Stolte, Fabio Graziosi, Cristian Antonelli, Pierre Sillard, Giuseppe Ferri, Benjamin J. Puttnam, Roland Ryf, Lauren Dallachiesa, Satoshi Shinada

Researchers from NICT, University of L’Aquila, Finisar, Prysmian and Nokia Bell Lab demonstrate a 2-line side 15-mode spatial division multiplexing network node based on fifteen 2×2 wavelength cross-connects to direct up to six 5 Tb/s, 15-mode,...

Mai 2023

Experimental and Numerical Evaluation of CAZAC-type Training Sequences for MxM SDM-MIMO Channel Estimation

Nicolas Braig-Christophersen, Colja Schubert, Carsten Schmidt-Langhorst, Robert Elschner, Johannes Fischer, Robert Emmerich, Andreas Maaßen, Juan L. Morrone

In this work, we experimentally and numerically compare cyclic shifted constant-amplitude zero-autocorrelation (CAZAC) training sequences (TS) with different number of repetitions, sequence lengths and scalings for channel estimation in an...

Mai 2023

Semantic modeling of cell damage prediction: A machine learning approach at human-level performance in dermatology

Patrick Wagner, Jackie Ma, Maximilian Springenberg, Marius Kröger, Rose K. C. Moritz, Johannes Schleusener, Martina C. Meinke

In this work we investigate cell damage in whole slice images of the epidermis. A common way for pathologists to annotate a score, characterising the degree of damage for these samples, is the ratio between healthy and unhealthy nuclei. The...

Mai 2023

Data Models for Dataset Drift Controls in Machine Learning With Optical Images

Luis Oala, Wojciech Samek, Gabriel Nobis, Christian Matek, Bruno Sanguinetti, Marco Aversa, Kurt Willis, Yoan Neuenschwander, Michèle Buck, Jerome Extermann, Enrico Pomarico, Roderick Murray-Smith, Christoph Clausen

In this study, we pair traditional machine learning with physical optics to obtain explicit and differentiable data models. We demonstrate how such data models can be constructed for image data and used to control downstream machine learning...

Ergebnisse pro Seite10ǀ20ǀ30
Ergebnisse 21-30 von 221
<< < 1 2 3 4 5 6 7 8 > >>