2026-09-22T03:10:11Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:25767 2026-09-05T19:24:26Z ddc:004 open_access

(Actual) Neurosymbolic AI: Combining Deep Learning and Knowledge Graphs (Dagstuhl Seminar 25291) Hitzler, Pascal Shimizu, Cogan Stepanova, Daria van Harmelen, Frank deep learning knowledge graphs neurosymbolic ai In the past decade, both deep learning (DL) and knowledge graphs (KGs) have seen astonishing growth and groundbreaking milestones – DL due to newly available resources (e.g., accessibility of (modern) web scale data), previously un-scalable techniques (e.g., transformers), and modern hardware; KGs due to successful standardization, web-scale integration, and previously un-scalable techniques for querying and inference. This has brought new and increased interest to both fields, and especially in how they can complement each other. % This report documents the program and the outcomes of Dagstuhl Seminar 25291 "(Actual) Neurosymbolic AI: Combining Deep Learning and Knowledge Graphs". This Dagstuhl Seminar brought 34 internationally recognized experts together to examine the gap between deep learning and knowledge graphs, and architect their integration: neurosymbolic AI. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Pascal Hitzler and Cogan Shimizu and Daria Stepanova and Frank van Harmelen 2026 Is Part Of Dagstuhl Reports, Volume 15, Issue 7 (2026) Article Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DagRep.15.7.53 urn:nbn:de:0030-drops-257675 https://drops.dagstuhl.de/entities/document/10.4230/DagRep.15.7.53 eng https://creativecommons.org/licenses/by/4.0/legalcode