← Search

Matthias Kaschube

2 accepted papers

2025

Dimensionality Mismatch Between Brains and Artificial Neural Networks

NeurIPS 2025poster

Biological and artificial vision systems both rely on hierarchical architectures, yet it remains unclear how their representational geometry evolves across processing stages, and what functional consequences may arise from potential differences. In this work, we systematically quantify and compare t…

Cited by 0SourceScholar
2024

Linking in Style: Understanding learned features in deep learning models

ECCV 2024poster

"Convolutional neural networks (CNNs) learn abstract features to perform object classification, but understanding these features remains challenging due to difficult-to-interpret results or high computational costs. We propose an automatic method to visualize and systematically analyze learned featu…