An interesting feature that traditional approaches to inductive logic programming are missing is the ability to treat noisy and non-logical data. Neural-symbolic approaches to inductive logic programming have been recently proposed to combine the advantages of inductive logic programming, in terms of interpretability and generalization capability, with the characteristic capacity of deep learning to treat noisy and non-logical data. This paper concisely surveys and briefly compares three promising neural-symbolic approaches to inductive logic programming that have been proposed in the last five years. The considered approaches use Datalog dialects to represent background knowledge, and they are capable of producing reusable logical rules from noisy and non-logical data. Therefore, they provide an effective means to combine logical reasoning with state-of-the-art machine learning.
A Comparative Study of Three Neural-Symbolic Approaches to Inductive Logic Programming / Beretta, D.; Monica, S.; Bergenti, F.. - 13416:(2022), pp. 56-61. (Intervento presentato al convegno 16th International Conference on Logic Programming and Nonmonotonic Reasoning, LPNMR 2022 tenutosi a ita nel 2022) [10.1007/978-3-031-15707-3_5].
A Comparative Study of Three Neural-Symbolic Approaches to Inductive Logic Programming
Monica S.;Bergenti F.
2022
Abstract
An interesting feature that traditional approaches to inductive logic programming are missing is the ability to treat noisy and non-logical data. Neural-symbolic approaches to inductive logic programming have been recently proposed to combine the advantages of inductive logic programming, in terms of interpretability and generalization capability, with the characteristic capacity of deep learning to treat noisy and non-logical data. This paper concisely surveys and briefly compares three promising neural-symbolic approaches to inductive logic programming that have been proposed in the last five years. The considered approaches use Datalog dialects to represent background knowledge, and they are capable of producing reusable logical rules from noisy and non-logical data. Therefore, they provide an effective means to combine logical reasoning with state-of-the-art machine learning.File | Dimensione | Formato | |
---|---|---|---|
LPNMR2022.pdf
Accesso riservato
Descrizione: Preprint
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
174.45 kB
Formato
Adobe PDF
|
174.45 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris