Michal Lewandowski — accepted AI-conference papers

2026

Exploiting Space Folding by Neural Networks

Michal Lewandowski, Raphael Pisoni, Bernhard Heinzl, Bernhard A. Moser

AAAI 2026technical

Recent findings suggest that consecutive layers of neural networks with the ReLU activation function fold the input space during the learning process. While many works hint at this phenomenon, an approach to quantify the folding was only recently proposed by means of a space folding measure based on

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Tessellation-Filtering ReLU Neural Networks

Bernhard A. Moser, Michal Lewandowski, Somayeh Kargaran, Werner Zellinger, Battista Biggio, Christoph Koutschan

IJCAI 2022poster

We identify tessellation-filtering ReLU neural networks that, when composed with another ReLU network, keep its non-redundant tessellation unchanged or reduce it.The additional network complexity modifies the shape of the decision surface without increasing the number of linear regions. We provid…

Cited by 4 Source ↗PDF ↗Scholar ↗