2026-07-22T16:11:56Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:17713 2026-04-20T13:22:16Z ddc:004 open_access

Differential Equations and Continuous-Time Deep Learning (Dagstuhl Seminar 22332) Duvenaud, David Heinonen, Markus Tiemann, Michael Welling, Max deep learning differential equations This report documents the program and the outcomes of Dagstuhl Seminar 22332 "Differential Equations and Continuous-Time Deep Learning". Neural ordinary-differential equations and similar continuous model architectures have gained interest in recent years, due to the existence of a vast literature in calculus and numerical analysis. Thus, continuous models might lead to architectures with finer control over prior assumptions or theoretical understanding. In this seminar, we have sought to bring together researchers from traditionally disjoint areas - machine learning, numerical analysis, dynamical systems and their "consumers" - to try and develop a joint language about this novel modeling paradigm. Through talks & group discussions, we have identified common interests and we hope that this first seminar is but the first step on a joint journey. Schloss Dagstuhl – Leibniz-Zentrum für Informatik David Duvenaud and Markus Heinonen and Michael Tiemann and Max Welling 2023 Is Part Of Dagstuhl Reports, Volume 12, Issue 8 (2023) Article Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DagRep.12.8.20 urn:nbn:de:0030-drops-177131 https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.8.20 eng https://creativecommons.org/licenses/by/4.0/legalcode