Lifted relational neural networks: efficient learning of latent relational structures
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 97062559
- Type
- D - Journal article
- DOI
-
10.1613/jair.1.11203
- Title of journal
- Journal of Artificial Intelligence Research
- Article number
- -
- First page
- 69
- Volume
- 62
- Issue
- -
- ISSN
- 1076-9757
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2018
- URL
-
http://dx.doi.org/10.1613/jair.1.11203
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
A - Artificial intelligence and data analytics
- Citation count
- 4
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper proposes a strategy for combining the effectiveness of neural network learning with the explainability of rule-based methods, with the aim of learning latent representations of relational structures. The proposed model was, among others, used in our conference paper at the ILP 2017 conference, which received the best paper award (https://ilp2017.sciencesconf.org/).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -