Learning predictive categories using lifted relational neural networks

Sourek, Gustav, Manandhar, Suresh, Zelezny, Filip, Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 and Kuzelka, Ondrej 2017. Learning predictive categories using lifted relational neural networks. Presented at: ILP 2016: International Conference on Inductive Logic Programming, London, UK, 4-6 September 2016. Published in: Cussens, James and Russo, Alexandra eds. Inductive Logic Programming. Lecture Notes in Computer Science. Lecture Notes in Computer Science , vol.10326 Cham: Springer, pp. 108-119. 10.1007/978-3-319-63342-8_9

Preview

PDF - Accepted Post-Print Version Download (314kB) | Preview

Abstract

Lifted relational neural networks (LRNNs) are a flexible neural-symbolic framework based on the idea of lifted modelling. In this paper we show how LRNNs can be easily used to specify declaratively and solve learning problems in which latent categories of entities, properties and relations need to be jointly induced.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher:	Springer
ISBN:	978-3-319-63342-8
ISSN:	0302-9743
Date of First Compliant Deposit:	11 January 2017
Last Modified:	02 Nov 2022 10:01
URI:	https://orca.cardiff.ac.uk/id/eprint/97185

Citation Data

Cited 8 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item