Search Results for author: Winfried Lötzsch

Found 6 papers, 2 papers with code

Towards Learning Self-Organized Criticality of Rydberg Atoms using Graph Neural Networks

no code implementations5 Jul 2022 Simon Ohler, Daniel Brady, Winfried Lötzsch, Michael Fleischhauer, Johannes S. Otterbach

Self-Organized Criticality (SOC) is a ubiquitous dynamical phenomenon believed to be responsible for the emergence of universal scale-invariant behavior in many, seemingly unrelated systems, such as forest fires, virus spreading or atomic excitation dynamics.

Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks

1 code implementation28 Jun 2022 Winfried Lötzsch, Simon Ohler, Johannes S. Otterbach

Specifically, we test generalization to meshes with different shapes and superposition of solutions for a different number of inhomogeneities.

Maps for Learning Indexable Classes

no code implementations15 Oct 2020 Julian Berger, Maximilian Böther, Vanja Doskoč, Jonathan Gadea Harder, Nicolas Klodt, Timo Kötzing, Winfried Lötzsch, Jannik Peters, Leon Schiller, Lars Seifert, Armin Wells, Simon Wietheger

We study learning of indexed families from positive data where a learner can freely choose a hypothesis space (with uniformly decidable membership) comprising at least the languages to be learned.

Learning Languages with Decidable Hypotheses

no code implementations15 Oct 2020 Julian Berger, Maximilian Böther, Vanja Doskoč, Jonathan Gadea Harder, Nicolas Klodt, Timo Kötzing, Winfried Lötzsch, Jannik Peters, Leon Schiller, Lars Seifert, Armin Wells, Simon Wietheger

This so-called $W$-index allows for naming arbitrary computably enumerable languages, with the drawback that even the membership problem is undecidable.

Cannot find the paper you are looking for? You can Submit a new open access paper.