Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310430005> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4310430005 abstract "Knowledge about space and time is necessary to solve problems in the physical world: An AI agent situated in the physical world and interacting with objects often needs to reason about positions of and relations between objects; and as soon as the agent plans its actions to solve a task, it needs to consider the temporal aspect (e.g., what actions to perform over time). Spatio-temporal knowledge, however, is required beyond interacting with the physical world, and is also often transferred to the abstract world of concepts through analogies and metaphors (e.g., a threat that is hanging over our heads). As spatial and temporal reasoning is ubiquitous, different attempts have been made to integrate this into AI systems. In the area of knowledge representation, spatial and temporal reasoning has been largely limited to modeling objects and relations and developing reasoning methods to verify statements about objects and relations. On the other hand, neural network researchers have tried to teach models to learn spatial relations from data with limited reasoning capabilities. Bridging the gap between these two approaches in a mutually beneficial way could allow us to tackle many complex real-world problems, such as natural language processing, visual question answering, and semantic image segmentation. In this chapter, we view this integration problem from the perspective of Neuro-Symbolic AI. Specifically, we propose a synergy between logical reasoning and machine learning that will be grounded on spatial and temporal knowledge. Describing some successful applications, remaining challenges, and evaluation datasets pertaining to this direction is the main topic of this contribution." @default.
- W4310430005 created "2022-12-10" @default.
- W4310430005 creator A5033486668 @default.
- W4310430005 creator A5035132175 @default.
- W4310430005 creator A5040045142 @default.
- W4310430005 creator A5071630431 @default.
- W4310430005 creator A5086661628 @default.
- W4310430005 creator A5087883689 @default.
- W4310430005 date "2022-11-28" @default.
- W4310430005 modified "2023-10-18" @default.
- W4310430005 title "Neuro-Symbolic Spatio-Temporal Reasoning" @default.
- W4310430005 doi "https://doi.org/10.48550/arxiv.2211.15566" @default.
- W4310430005 hasPublicationYear "2022" @default.
- W4310430005 type Work @default.
- W4310430005 citedByCount "0" @default.
- W4310430005 crossrefType "posted-content" @default.
- W4310430005 hasAuthorship W4310430005A5033486668 @default.
- W4310430005 hasAuthorship W4310430005A5035132175 @default.
- W4310430005 hasAuthorship W4310430005A5040045142 @default.
- W4310430005 hasAuthorship W4310430005A5071630431 @default.
- W4310430005 hasAuthorship W4310430005A5086661628 @default.
- W4310430005 hasAuthorship W4310430005A5087883689 @default.
- W4310430005 hasBestOaLocation W43104300051 @default.
- W4310430005 hasConcept C12713177 @default.
- W4310430005 hasConcept C132829578 @default.
- W4310430005 hasConcept C154945302 @default.
- W4310430005 hasConcept C155911833 @default.
- W4310430005 hasConcept C161301231 @default.
- W4310430005 hasConcept C174348530 @default.
- W4310430005 hasConcept C17744445 @default.
- W4310430005 hasConcept C199539241 @default.
- W4310430005 hasConcept C27511587 @default.
- W4310430005 hasConcept C2776359362 @default.
- W4310430005 hasConcept C31258907 @default.
- W4310430005 hasConcept C41008148 @default.
- W4310430005 hasConcept C94625758 @default.
- W4310430005 hasConceptScore W4310430005C12713177 @default.
- W4310430005 hasConceptScore W4310430005C132829578 @default.
- W4310430005 hasConceptScore W4310430005C154945302 @default.
- W4310430005 hasConceptScore W4310430005C155911833 @default.
- W4310430005 hasConceptScore W4310430005C161301231 @default.
- W4310430005 hasConceptScore W4310430005C174348530 @default.
- W4310430005 hasConceptScore W4310430005C17744445 @default.
- W4310430005 hasConceptScore W4310430005C199539241 @default.
- W4310430005 hasConceptScore W4310430005C27511587 @default.
- W4310430005 hasConceptScore W4310430005C2776359362 @default.
- W4310430005 hasConceptScore W4310430005C31258907 @default.
- W4310430005 hasConceptScore W4310430005C41008148 @default.
- W4310430005 hasConceptScore W4310430005C94625758 @default.
- W4310430005 hasLocation W43104300051 @default.
- W4310430005 hasOpenAccess W4310430005 @default.
- W4310430005 hasPrimaryLocation W43104300051 @default.
- W4310430005 hasRelatedWork W1480251338 @default.
- W4310430005 hasRelatedWork W1871668702 @default.
- W4310430005 hasRelatedWork W1990878416 @default.
- W4310430005 hasRelatedWork W2112464467 @default.
- W4310430005 hasRelatedWork W2313795055 @default.
- W4310430005 hasRelatedWork W2358327782 @default.
- W4310430005 hasRelatedWork W2383025195 @default.
- W4310430005 hasRelatedWork W2398254870 @default.
- W4310430005 hasRelatedWork W303774563 @default.
- W4310430005 hasRelatedWork W2124449677 @default.
- W4310430005 isParatext "false" @default.
- W4310430005 isRetracted "false" @default.
- W4310430005 workType "article" @default.