Published November 6, 2025
| Version v2
Software
Open
ReLU Region Reason (Re3)
Authors/Creators
Description
ReLU Region Reason (Re3) has been introduced in this study. This method takes advantage of the piecewise-linear nature of ReLU networks to gain insights into how neurons are activated and accurately calculate how each feature contributes to the final
score and probability.
If you use this code in your research, please cite:
```bibtex
@article{Barua7328,
author = {Arnab Barua and Mobyen Uddin Ahmed and Shahina Begum},
title = {Mechanistic Interpretability of ReLU Neural Networks Through Piecewise-Affine Mapping},
pages = {1--35},
month = {January},
year = {2026},
journal = {Machine Learning},
url = {http://www.es.mdu.se/publications/7328-}
}
author = {Arnab Barua and Mobyen Uddin Ahmed and Shahina Begum},
title = {Mechanistic Interpretability of ReLU Neural Networks Through Piecewise-Affine Mapping},
pages = {1--35},
month = {January},
year = {2026},
journal = {Machine Learning},
url = {http://www.es.mdu.se/publications/7328-}
}
```
Barua, A., Ahmed, M.U. & Begum, S. Mechanistic Interpretability of ReLU Neural Networks Through Piecewise-Affine Mapping. Mach Learn 115, 17 (2026). https://doi.org/10.1007/s10994-025-06957-0
Files
accelerometer_gyro_mobile_phone_dataset.csv
Files
(25.7 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:dc8b9464ebcfd3a61ce5b4e1b0e7cb17
|
2.1 MB | Preview Download |
|
md5:8f90e44047182c5f32d10f0c4dd4890f
|
22.7 MB | Preview Download |
|
md5:341a3b5244f213282b7b0920b729c592
|
4.0 kB | Preview Download |
|
md5:fff2e355450d594c82c283855512ddd2
|
36.2 kB | Preview Download |
|
md5:4ffff04a198e9cdf2fb01f05ee0e7001
|
41.2 kB | Preview Download |
|
md5:f848be81662465406aec774298c56491
|
48.5 kB | Preview Download |
|
md5:698922d0acab3043687f29a2a9effba1
|
3.7 kB | Preview Download |
|
md5:f5b056f6834f00c5a8cc73c45694708c
|
140 Bytes | Preview Download |
|
md5:24f6f70fcf40fa115de5c71859dc7108
|
9.3 kB | Preview Download |
|
md5:e7368d48fa690b0331a09b430d55fb6a
|
702.9 kB | Download |
|
md5:0a71c3eccab2b35d9eaf5f4dee070bc5
|
6.4 kB | Download |
|
md5:4f4a688ed988164deb0b7c77a7135bfc
|
3.6 kB | Download |
Additional details
Funding
Software
- Programming language
- Python