activity
20242026
collaborators

6 papers

cs.LG2026

Distributional Loss for Robust Classification

Kathleen Anderson, Thomas Martinetz

This paper proposes a novel loss concept for supervised classification tasks. Rather than enforcing a direct mapping from each input sample to a single assigned label, we define an…

cs.LG2026

Nearest-Neighbor Density Estimation for Dependency Suppression

Kathleen Anderson, Thomas Martinetz

The ability to remove unwanted dependencies from data is crucial in various domains, including fairness, robust learning, and privacy protection. In this work, we propose an encode…

cs.LG2025

The Resurrection of the ReLU

Coşku Can Horuz, Geoffrey Kasenbacher, Saya Higuchi +7

Modeling sophisticated activation functions within deep learning architectures has evolved into a distinct research direction. Functions such as GELU, SELU, and SiLU offer smooth g…

cs.CV2025

Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations

Kathleen Anderson, Thomas Martinetz

We evaluate the information that can unintentionally leak into the low dimensional output of a neural network, by reconstructing an input image from a 40- or 32-element feature vec…

cs.LG2025

Why LLMs Cannot Think and How to Fix It

Marius Jahrens, Thomas Martinetz

This paper elucidates that current state-of-the-art Large Language Models (LLMs) are fundamentally incapable of making decisions or developing "thoughts" within the feature space d…

cs.CV2024

Enhancing Generalization in Convolutional Neural Networks through Regularization with Edge and Line Features

Christoph Linse, Beatrice Brückner, Thomas Martinetz

This paper proposes a novel regularization approach to bias Convolutional Neural Networks (CNNs) toward utilizing edge and line features in their hidden layers. Rather than learnin…