Proving properties of binary classification neural networks via Łukasiewicz logic (2023)
- Authors:
- USP affiliated authors: FINGER, MARCELO - IME ; PRETO, SANDRO MÁRCIO DA SILVA - IME
- Unidade: IME
- DOI: 10.1093/jigpal/jzac050
- Assunto: LÓGICA MATEMÁTICA
- Keywords: Łukasiewicz infinitely-valued logic; rational McNaughton functions; neural networks; formal methods; reachability; robustness
- Agências de fomento:
- Language: Inglês
- Imprenta:
- Source:
- Título: Logic Journal of the IGPL
- ISSN: 1367-0751
- Volume/Número/Paginação/Ano: v. 31, n. 5, p. 805-821, 2023
- Este periódico é de assinatura
- Este artigo NÃO é de acesso aberto
- Cor do Acesso Aberto: closed
-
ABNT
PRETO, Sandro e FINGER, Marcelo. Proving properties of binary classification neural networks via Łukasiewicz logic. Logic Journal of the IGPL, v. 31, n. 5, p. 805-821, 2023Tradução . . Disponível em: https://doi.org/10.1093/jigpal/jzac050. Acesso em: 12 nov. 2024. -
APA
Preto, S., & Finger, M. (2023). Proving properties of binary classification neural networks via Łukasiewicz logic. Logic Journal of the IGPL, 31( 5), 805-821. doi:10.1093/jigpal/jzac050 -
NLM
Preto S, Finger M. Proving properties of binary classification neural networks via Łukasiewicz logic [Internet]. Logic Journal of the IGPL. 2023 ; 31( 5): 805-821.[citado 2024 nov. 12 ] Available from: https://doi.org/10.1093/jigpal/jzac050 -
Vancouver
Preto S, Finger M. Proving properties of binary classification neural networks via Łukasiewicz logic [Internet]. Logic Journal of the IGPL. 2023 ; 31( 5): 805-821.[citado 2024 nov. 12 ] Available from: https://doi.org/10.1093/jigpal/jzac050 - Polyhedral semantics and the tractable approximation of Łukasiewicz infinitely-valued logic
- Linking Łukasiewicz logic and boolean maximum satisfiability
- Effective reasoning over neural networks using Lukasiewicz logic
- Coherence of probabilistic constraints on Nash equilibria
- Representing rational McNaughton functions via MODSAT relativisation
- Probably half true: probabilistic satisfiability over Łukasiewicz infinitely-valued logic
- Probably partially true: satisfiability for Łukasiewicz infinitely-valued probabilistic logic and related topics
- Benchmarking Łukasiewicz logic solvers with properties of neural networks
- Efficient representation of piecewise linear functions into Łukasiewicz logic modulo satisfiability
- An efficient algorithm for representing piecewise linear functions into logic
Informações sobre o DOI: 10.1093/jigpal/jzac050 (Fonte: oaDOI API)
Download do texto completo
| Tipo | Nome | Link | |
|---|---|---|---|
 |
3082021.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
