Sökning: WFRF:(Manhaeve Robin)
> (2023) >
Neural Probabilisti...
Neural Probabilistic Logic Programming in Discrete-Continuous Domains
-
- De Smet, Lennert (författare)
- Department of Computer Science, KU Leuven, Belgium
-
- Zuidberg dos Martires, Pedro, 1990- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Machine Perception and Interaction Lab
-
- Manhaeve, Robin (författare)
- Department of Computer Science, KU Leuven, Belgium
-
visa fler...
-
- Marra, Giuseppe (författare)
- Department of Computer Science, KU Leuven, Belgium
-
- Kimmig, Angelika (författare)
- Department of Computer Science, KU Leuven, Belgium
-
- De Raedt, Luc, 1964- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Department of Computer Science, KU Leuven, Belgium,Machine Perception and Interaction Lab
-
visa färre...
-
(creator_code:org_t)
- JMLR, 2023
- 2023
- Engelska.
-
Ingår i: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence. - : JMLR. ; , s. 529-538
- Relaterad länk:
-
https://doi.org/10.4...
-
visa fler...
-
https://oru.diva-por... (primary) (Raw object)
-
https://urn.kb.se/re...
-
https://doi.org/10.4...
-
visa färre...
Abstract
Ämnesord
Stäng
- Neural-symbolic AI (NeSy) allows neural net-works to exploit symbolic background knowledge in the form of logic. It has been shown to aid learning in the limited data regime and to facilitate inference on out-of-distribution data. Probabilistic NeSy focuses on integrating neural networks with both logic and probability theory, which additionally allows learning under uncertainty. A major limitation of current probabilistic NeSy systems, such as DeepProbLog, is their restriction to finite probability distributions, i.e., discrete random variables. In contrast, deep probabilistic programming (DPP) excels in modelling and optimising continuous probability distributions. Hence, we introduce DeepSeaProbLog, a neural probabilistic logic programming language that incorporates DPP techniques into NeSy. Doing so results in the support of inference and learning of both discrete and continuous probability distributions under logical constraints. Our main contributions are 1) the semantics of DeepSeaProbLog and its corresponding inference algorithm, 2) a proven asymptotically unbiased learning algorithm, and 3) a series of experiments that illustrate the versatility of our approach.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)