Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289643732> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4289643732 endingPage "13" @default.
- W4289643732 startingPage "1" @default.
- W4289643732 abstract "Neural–symbolic models provide a powerful tool to tackle complex visual reasoning tasks by combining symbolic program execution for reasoning and deep representation learning for visual recognition. A probabilistic formulation of such models with stochastic latent variables can obtain an interpretable and legible reasoning system with less supervision. However, it is still nontrivial to generate reasonable symbolic structures without the guidance of domain knowledge, since it generally involves an optimization problem with both continuous and discrete variables. Despite the challenges, the interpretability of such symbolic structures provides an interface to regularize their generation by domain knowledge. In this article, we propose to incorporate the available domain knowledge into the learning process of probabilistic neural–symbolic (PNS) models via posterior constraints that directly regularize the structure posterior. In this way, our model is able to identify a middle point where the structure generation process mainly learns from data but also selectively borrows information from domain knowledge. We further present inductive reasoning where the posterior constraints can be automatically reweighted to handle noisy annotations. The experimental results show that our method achieves state-of-the-art performance on major abstract reasoning datasets and enjoys good generalization capability and data efficiency." @default.
- W4289643732 created "2022-08-03" @default.
- W4289643732 creator A5011877804 @default.
- W4289643732 creator A5017046908 @default.
- W4289643732 creator A5035606234 @default.
- W4289643732 creator A5050801351 @default.
- W4289643732 creator A5072905534 @default.
- W4289643732 date "2022-01-01" @default.
- W4289643732 modified "2023-10-15" @default.
- W4289643732 title "Probabilistic Neural–Symbolic Models With Inductive Posterior Constraints" @default.
- W4289643732 doi "https://doi.org/10.1109/tnnls.2022.3190820" @default.
- W4289643732 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35914034" @default.
- W4289643732 hasPublicationYear "2022" @default.
- W4289643732 type Work @default.
- W4289643732 citedByCount "0" @default.
- W4289643732 crossrefType "journal-article" @default.
- W4289643732 hasAuthorship W4289643732A5011877804 @default.
- W4289643732 hasAuthorship W4289643732A5017046908 @default.
- W4289643732 hasAuthorship W4289643732A5035606234 @default.
- W4289643732 hasAuthorship W4289643732A5050801351 @default.
- W4289643732 hasAuthorship W4289643732A5072905534 @default.
- W4289643732 hasConcept C119857082 @default.
- W4289643732 hasConcept C134306372 @default.
- W4289643732 hasConcept C154945302 @default.
- W4289643732 hasConcept C177148314 @default.
- W4289643732 hasConcept C17744445 @default.
- W4289643732 hasConcept C199539241 @default.
- W4289643732 hasConcept C207685749 @default.
- W4289643732 hasConcept C2776359362 @default.
- W4289643732 hasConcept C2781067378 @default.
- W4289643732 hasConcept C33923547 @default.
- W4289643732 hasConcept C36503486 @default.
- W4289643732 hasConcept C41008148 @default.
- W4289643732 hasConcept C49937458 @default.
- W4289643732 hasConcept C94625758 @default.
- W4289643732 hasConceptScore W4289643732C119857082 @default.
- W4289643732 hasConceptScore W4289643732C134306372 @default.
- W4289643732 hasConceptScore W4289643732C154945302 @default.
- W4289643732 hasConceptScore W4289643732C177148314 @default.
- W4289643732 hasConceptScore W4289643732C17744445 @default.
- W4289643732 hasConceptScore W4289643732C199539241 @default.
- W4289643732 hasConceptScore W4289643732C207685749 @default.
- W4289643732 hasConceptScore W4289643732C2776359362 @default.
- W4289643732 hasConceptScore W4289643732C2781067378 @default.
- W4289643732 hasConceptScore W4289643732C33923547 @default.
- W4289643732 hasConceptScore W4289643732C36503486 @default.
- W4289643732 hasConceptScore W4289643732C41008148 @default.
- W4289643732 hasConceptScore W4289643732C49937458 @default.
- W4289643732 hasConceptScore W4289643732C94625758 @default.
- W4289643732 hasFunder F4320335777 @default.
- W4289643732 hasLocation W42896437321 @default.
- W4289643732 hasLocation W42896437322 @default.
- W4289643732 hasOpenAccess W4289643732 @default.
- W4289643732 hasPrimaryLocation W42896437321 @default.
- W4289643732 hasRelatedWork W2605281151 @default.
- W4289643732 hasRelatedWork W3006943036 @default.
- W4289643732 hasRelatedWork W3012234327 @default.
- W4289643732 hasRelatedWork W3119715496 @default.
- W4289643732 hasRelatedWork W3191046242 @default.
- W4289643732 hasRelatedWork W382458928 @default.
- W4289643732 hasRelatedWork W4205364923 @default.
- W4289643732 hasRelatedWork W4206534706 @default.
- W4289643732 hasRelatedWork W4229079080 @default.
- W4289643732 hasRelatedWork W4294031299 @default.
- W4289643732 isParatext "false" @default.
- W4289643732 isRetracted "false" @default.
- W4289643732 workType "article" @default.