Neural Interpretable Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916642106114048 |
|---|---|
| author | Barbiero, Pietro Marra, Giuseppe Ciravegna, Gabriele Debot, David De Santis, Francesco Diligenti, Michelangelo Zarlenga, Mateo Espinosa Giannini, Francesco |
| author_facet | Barbiero, Pietro Marra, Giuseppe Ciravegna, Gabriele Debot, David De Santis, Francesco Diligenti, Michelangelo Zarlenga, Mateo Espinosa Giannini, Francesco |
| contents | We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of interpretability scales exponentially with the number of variables of the system, we show that this complexity can be mitigated by treating interpretability as a Markovian property and employing neural re-parametrization techniques. Building on these insights, we propose a new modeling paradigm -- neural generation and interpretable execution -- that enables scalable verification of equivariance. This paradigm provides a general approach for designing Neural Interpretable Reasoners that are not only expressive but also transparent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11639 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Interpretable Reasoning Barbiero, Pietro Marra, Giuseppe Ciravegna, Gabriele Debot, David De Santis, Francesco Diligenti, Michelangelo Zarlenga, Mateo Espinosa Giannini, Francesco Machine Learning Artificial Intelligence Neural and Evolutionary Computing We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of interpretability scales exponentially with the number of variables of the system, we show that this complexity can be mitigated by treating interpretability as a Markovian property and employing neural re-parametrization techniques. Building on these insights, we propose a new modeling paradigm -- neural generation and interpretable execution -- that enables scalable verification of equivariance. This paradigm provides a general approach for designing Neural Interpretable Reasoners that are not only expressive but also transparent. |
| title | Neural Interpretable Reasoning |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2502.11639 |