no code implementations • 22 Aug 2023 • Adrián Csiszárik, Melinda F. Kiss, Péter Kőrösi-Szabó, Márton Muntag, Gergely Papp, Dániel Varga
We explore element-wise convex combinations of two permutation-aligned neural network parameter vectors $\Theta_A$ and $\Theta_B$ of size $d$.
1 code implementation • NeurIPS 2021 • Adrián Csiszárik, Péter Kőrösi-Szabó, Ákos K. Matszangosz, Gergely Papp, Dániel Varga
With this toolset, we aim to match the activations on given layers of two trained neural networks by joining them with a stitching layer.
no code implementations • 15 Jul 2020 • Róbert Szabó, Dániel Katona, Márton Csillag, Adrián Csiszárik, Dániel Varga
We provide visualizations of individual neurons of a deep image recognition network during the temporal process of transfer learning.
no code implementations • 7 Oct 2019 • Adrián Csiszárik, Beatrix Benkő, Dániel Varga
Modern deep artificial neural networks have achieved great success in the domain of computer vision and beyond.
no code implementations • 28 Dec 2017 • Dániel Varga, Adrián Csiszárik, Zsolt Zombori
Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times.