Computing Linear Regions in Neural Networks with Skip Connections
Not on the map. Why?
Abstract (arXiv)
Neural networks are important tools in machine learning. Representing piecewise linear activation functions with tropical arithmetic enables the application of tropical geometry. Algorithms are presented to compute regions where the neural networks are linear maps. Through computational experiments, we provide insights on the difficulty to train neural networks, in particular on the problems of overfitting and on the benefits of skip connections.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 6 of its 15 references that are in the map. First posted on arXiv 18 Sep 2025.
Builds on
6 of 15 references.
References · 6
- 2014On the Number of Linear Regions of Deep Neural Networkscited by 381
- 2017Bounding and Counting Linear Regions of Deep Neural Networkscited by 161
- 2018Tropical Geometry of Deep Neural Networkscited by 95
- 2018Mad Max: Affine Spline Insights into Deep Learningcited by 55
- 2020Empirical Studies on the Properties of Linear Regions in Deep Neural Networkscited by 36
- 2023Training Dynamics of Deep Network Linear Regionscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.