Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205374622> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3205374622 abstract "DeepProbLog is a neural-symbolic framework that integrates probabilistic logic programming and neural networks. It is realized by providing an interface between the probabilistic logic and the neural networks. Inference in probabilistic neural symbolic methods is hard, since it combines logical theorem proving with probabilistic inference and neural network evaluation. In this work, we make the inference more efficient by extending an approximate inference algorithm from the field of statistical-relational AI. Instead of considering all possible proofs for a certain query, the system searches for the best proof. However, training a DeepProbLog model using approximate inference introduces additional challenges, as the best proof is unknown at the start of training which can lead to convergence towards a local optimum. To be able to apply DeepProbLog on larger tasks, we propose: 1) a method for approximate inference using an A*-like search, called DPLA* 2) an exploration strategy for proving in a neural-symbolic setting, and 3) a parametric heuristic to guide the proof search. We empirically evaluate the performance and scalability of the new approach, and also compare the resulting approach to other neural-symbolic systems. The experiments show that DPLA* achieves a speed up of up to 2-3 orders of magnitude in some cases." @default.
- W3205374622 created "2021-10-25" @default.
- W3205374622 creator A5003576783 @default.
- W3205374622 creator A5005466305 @default.
- W3205374622 creator A5078136609 @default.
- W3205374622 date "2021-09-01" @default.
- W3205374622 modified "2023-09-27" @default.
- W3205374622 title "Approximate Inference for Neural Probabilistic Logic Programming" @default.
- W3205374622 cites W1510555031 @default.
- W3205374622 cites W1518043585 @default.
- W3205374622 cites W1529318459 @default.
- W3205374622 cites W1564663950 @default.
- W3205374622 cites W1824971879 @default.
- W3205374622 cites W1836582804 @default.
- W3205374622 cites W1990005915 @default.
- W3205374622 cites W2112796928 @default.
- W3205374622 cites W2465254145 @default.
- W3205374622 cites W2767656849 @default.
- W3205374622 cites W2946752867 @default.
- W3205374622 cites W2963560424 @default.
- W3205374622 cites W2964031560 @default.
- W3205374622 cites W2971107062 @default.
- W3205374622 cites W2997359684 @default.
- W3205374622 cites W3034903373 @default.
- W3205374622 cites W3035398729 @default.
- W3205374622 cites W3035758390 @default.
- W3205374622 cites W3099451540 @default.
- W3205374622 cites W3154009503 @default.
- W3205374622 cites W87020493 @default.
- W3205374622 doi "https://doi.org/10.24963/kr.2021/45" @default.
- W3205374622 hasPublicationYear "2021" @default.
- W3205374622 type Work @default.
- W3205374622 sameAs 3205374622 @default.
- W3205374622 citedByCount "0" @default.
- W3205374622 crossrefType "proceedings-article" @default.
- W3205374622 hasAuthorship W3205374622A5003576783 @default.
- W3205374622 hasAuthorship W3205374622A5005466305 @default.
- W3205374622 hasAuthorship W3205374622A5078136609 @default.
- W3205374622 hasBestOaLocation W32053746221 @default.
- W3205374622 hasConcept C102993220 @default.
- W3205374622 hasConcept C11413529 @default.
- W3205374622 hasConcept C119857082 @default.
- W3205374622 hasConcept C154945302 @default.
- W3205374622 hasConcept C173801870 @default.
- W3205374622 hasConcept C18998212 @default.
- W3205374622 hasConcept C203659156 @default.
- W3205374622 hasConcept C2776214188 @default.
- W3205374622 hasConcept C3845977 @default.
- W3205374622 hasConcept C41008148 @default.
- W3205374622 hasConcept C48044578 @default.
- W3205374622 hasConcept C49937458 @default.
- W3205374622 hasConcept C50644808 @default.
- W3205374622 hasConcept C77088390 @default.
- W3205374622 hasConcept C80444323 @default.
- W3205374622 hasConceptScore W3205374622C102993220 @default.
- W3205374622 hasConceptScore W3205374622C11413529 @default.
- W3205374622 hasConceptScore W3205374622C119857082 @default.
- W3205374622 hasConceptScore W3205374622C154945302 @default.
- W3205374622 hasConceptScore W3205374622C173801870 @default.
- W3205374622 hasConceptScore W3205374622C18998212 @default.
- W3205374622 hasConceptScore W3205374622C203659156 @default.
- W3205374622 hasConceptScore W3205374622C2776214188 @default.
- W3205374622 hasConceptScore W3205374622C3845977 @default.
- W3205374622 hasConceptScore W3205374622C41008148 @default.
- W3205374622 hasConceptScore W3205374622C48044578 @default.
- W3205374622 hasConceptScore W3205374622C49937458 @default.
- W3205374622 hasConceptScore W3205374622C50644808 @default.
- W3205374622 hasConceptScore W3205374622C77088390 @default.
- W3205374622 hasConceptScore W3205374622C80444323 @default.
- W3205374622 hasLocation W32053746221 @default.
- W3205374622 hasLocation W32053746222 @default.
- W3205374622 hasOpenAccess W3205374622 @default.
- W3205374622 hasPrimaryLocation W32053746221 @default.
- W3205374622 hasRelatedWork W1221614779 @default.
- W3205374622 hasRelatedWork W1541017616 @default.
- W3205374622 hasRelatedWork W1854944386 @default.
- W3205374622 hasRelatedWork W1889548941 @default.
- W3205374622 hasRelatedWork W2553103903 @default.
- W3205374622 hasRelatedWork W2810873133 @default.
- W3205374622 hasRelatedWork W2811454648 @default.
- W3205374622 hasRelatedWork W2950173302 @default.
- W3205374622 hasRelatedWork W3136652852 @default.
- W3205374622 hasRelatedWork W4297797389 @default.
- W3205374622 isParatext "false" @default.
- W3205374622 isRetracted "false" @default.
- W3205374622 magId "3205374622" @default.
- W3205374622 workType "article" @default.