Saved in:
Bibliographic Details
Main Authors: Labbaf, Faezeh, Kolárik, Tomáš, Blicha, Martin, Fedyukovich, Grigory, Wand, Michael, Sharygina, Natasha
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.22498
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908679380402176
author Labbaf, Faezeh
Kolárik, Tomáš
Blicha, Martin
Fedyukovich, Grigory
Wand, Michael
Sharygina, Natasha
author_facet Labbaf, Faezeh
Kolárik, Tomáš
Blicha, Martin
Fedyukovich, Grigory
Wand, Michael
Sharygina, Natasha
contents We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas of the input feature space. To automatically generate space explanations, we leverage a range of flexible Craig interpolation algorithms and unsatisfiable core generation. Based on real-life case studies, ranging from small to medium to large size, we demonstrate that the generated explanations are more meaningful than those computed by state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22498
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Space Explanations of Neural Network Classification
Labbaf, Faezeh
Kolárik, Tomáš
Blicha, Martin
Fedyukovich, Grigory
Wand, Michael
Sharygina, Natasha
Machine Learning
Logic in Computer Science
We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas of the input feature space. To automatically generate space explanations, we leverage a range of flexible Craig interpolation algorithms and unsatisfiable core generation. Based on real-life case studies, ranging from small to medium to large size, we demonstrate that the generated explanations are more meaningful than those computed by state-of-the-art.
title Space Explanations of Neural Network Classification
topic Machine Learning
Logic in Computer Science
url https://arxiv.org/abs/2511.22498