Sökning: onr:"swepub:oai:DiVA.org:oru-96659" >
Neural probabilisti...
Neural probabilistic logic programming in DeepProbLog
-
- Manhaeve, Robin (författare)
- KU Leuven, Belgium
-
- Dumančić, Sebastijan (författare)
- KU Leuven, Belgium
-
- Kimmig, Angelika (författare)
- KU Leuven, Belgium
-
visa fler...
-
- Demeester, Thomas (författare)
- Ghent University - imec, Belgium
-
- De Raedt, Luc, 1964- (författare)
- KU Leuven, Belgium,AASS
-
visa färre...
-
(creator_code:org_t)
- Elsevier, 2021
- 2021
- Engelska.
-
Ingår i: Artificial Intelligence. - : Elsevier. - 0004-3702 .- 1872-7921. ; 298
- Relaterad länk:
-
https://biblio.ugent...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques of the underlying probabilistic logic programming language ProbLog can be adapted for the new language. We theoretically and experimentally demonstrate that DeepProbLog supports (i) both symbolic and subsymbolic representations and inference, (ii) program induction, (iii) probabilistic (logic) programming, and (iv)(deep) learning from examples. To the best of our knowledge, this work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that exploits the full expressiveness and strengths of both worlds and can be trained end-to-end based on examples. (C) 2021 Elsevier B.V. All rights reserved.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Nyckelord
- Logic
- Probability
- Neural networks
- Probabilistic logic programming
- Neuro-symbolic integration
- Learning and reasoning
- Computer Science
- Datavetenskap
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas