SkelEx and BoundEx: Natural Visualization of ReLU Neural Networks
Not on the map. Why?
Abstract (arXiv)
Despite their limited interpretability, weights and biases are still the most popular encoding of the functions learned by ReLU Neural Networks (ReLU NNs). That is why we introduce SkelEx, an algorithm to extract a skeleton of the membership functions learned by ReLU NNs, making those functions easier to interpret and analyze. To the best of our knowledge, this is the first work that considers linear regions from the perspective of critical points. As a natural follow-up, we also introduce BoundEx, which is the first analytical method known to us to extract the decision boundary from the realization of a ReLU NN. Both of those methods introduce very natural visualization tool for ReLU NNs trained on low-dimensional data.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 9 May 2023.
Builds on
12 of 18 references.
References · 12
- 2014On the Number of Linear Regions of Deep Neural Networkscited by 378
- 2016On the Expressive Power of Deep Neural Networkscited by 302
- 2018Sensitivity and Generalization in Neural Networks: an Empirical Studycited by 187
- 2019Complexity of Linear Regions in Deep Networkscited by 166
- 2017Bounding and Counting Linear Regions of Deep Neural Networkscited by 161
- 2019Deep ReLU Networks Have Surprisingly Few Activation Patternscited by 160
- 2020Empirical Studies on the Properties of Linear Regions in Deep Neural Networkscited by 36
- 2020Hold me tight! Influence of discriminative features on deep network boundariescited by 31
- 2020Analysis of Generalizability of Deep Neural Networks Based on the Complexity of Decision Boundarycited by 13
- 2022Are All Linear Regions Created Equal?cited by 13
- 2019Optimal Function Approximation with Relu Neural Networkscited by 9
- 2020Super-k: A Piecewise Linear Classifier Based on Voronoi Tessellationscited by 2
Built on by
Not cited yet.