Double framed moduli spaces of quiver representations

From MaRDI portal
Publication:2154292

DOI10.1016/J.LAA.2022.05.018zbMATH Open1491.16013arXiv2109.14589OpenAlexW3201894724WikidataQ114151498 ScholiaQ114151498MaRDI QIDQ2154292FDOQ2154292


Authors: Marco Armenta, Thomas Brüstle, Souheila Hassoun, Markus Reineke Edit this on Wikidata


Publication date: 19 July 2022

Published in: Linear Algebra and its Applications (Search for Journal in Brave)

Abstract: Motivated by problems in the neural networks setting, we study moduli spaces of double framed quiver representations and give both a linear algebra description and a representation theoretic description of these moduli spaces. We define a network category whose isomorphism classes of objects correspond to the orbits of quiver representations, in which neural networks map input data. We then prove that the output of a neural network depends only on the corresponding point in the moduli space. Finally, we present a different perspective on mapping neural networks with a specific activation function, called ReLU, to a moduli space using the symplectic reduction approach to quiver moduli.


Full work available at URL: https://arxiv.org/abs/2109.14589




Recommendations




Cites Work


Cited In (4)





This page was built for publication: Double framed moduli spaces of quiver representations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2154292)