Metraipolis › archive › dc_12fe64e52d03
Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks — arXiv:2609.14099
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14099
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:15:24.942Z
- SHA-256 of the archived text
41271c5741c8d6f0d578916ea5cc7396323907be66eafb320d7db9ee6391b807- Stable URL of this page
https://metraipolis.com/documento/dc_12fe64e52d03
How to cite
Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks — arXiv:2609.14099 — arXiv (en), https://arxiv.org/abs/2609.14099 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_12fe64e52d03 (Metraipolis archive dc_12fe64e52d03, sha256 41271c5741c8d6f0d578916ea5cc7396323907be66eafb320d7db9ee6391b807)
BibTeX
@misc{dc12fe64e52d03,
title = {Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks — arXiv:2609.14099},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14099},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_12fe64e52d03; sha256 41271c5741c8d6f0d578916ea5cc7396323907be66eafb320d7db9ee6391b807},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14099. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Formal explainability of classifying neural networks (NNs) is an active area of research, providing explanations with provable guarantees of the classification within continuous regions of the input feature space. However, the existing techniques are either limited to individual input features without guarantees on their relations or the provided solutions fail to scale to deep architectures. This paper addresses these issues by introducing a flexible symbolic framework for an efficient, guided computation of explanations of the NN behavior, parametrized by the activations of internal neurons, and using logical engines such as SMT solvers. Unlike prior methods that rely on specialized NN verifiers, our method yields explanations that are not restricted in shape. Our algorithm is implementable on top of a general-purpose logical solver, isolating the NN-specific encoding from the algorithmic framework. We experimented with a wide range of benchmarks from the domains of image recognition and medicine, illustrating the advantages of the new method, particularly in computational efficiency. Notably, our approach enables logical explanation of deep networks not amenable to prior logic-based methods. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Logic in Computer Science (cs.LO) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.14099 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T23:54:14.884Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).