1 code implementation • 21 Oct 2022 • Andreas Søgaard, Rasmus F. Ørsøe, Leon Bozianu, Morten Holm, Kaare Endrup Iversen, Tim Guggenmos, Martin Ha Minh, Philipp Eller, Troels C. Petersen
GraphNeT is an open-source python framework aimed at providing high quality, user friendly, end-to-end functionality to perform reconstruction tasks at neutrino telescopes using graph neural networks (GNNs).
1 code implementation • 25 Mar 2017 • Andreas Søgaard
A novel method for learning optimal, orthonormal wavelet bases for representing 1- and 2D signals, based on parallels between the wavelet transform and fully connected artificial neural networks, is described.
no code implementations • 10 Mar 2017 • Chase Shimmin, Peter Sadowski, Pierre Baldi, Edison Weik, Daniel Whiteson, Edward Goul, Andreas Søgaard
We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass.