16 citations · 22 across the 3 of their papers we have counts for
3 papers
Mode Combinability: Exploring Convex Combinations of Permutation Aligned Models
Adrián Csiszárik, Melinda F. Kiss, Péter Kőrösi-Szabó +3
We explore element-wise convex combinations of two permutation-aligned neural network parameter vectors and of size . We conduct extensive experiments by examining v…
Similarity and Matching of Neural Network Representations
Adrián Csiszárik, Péter Kőrösi-Szabó, Ákos K. Matszangosz +2
We employ a toolset -- dubbed Dr. Frankenstein -- to analyse the similarity of representations in deep neural networks. With this toolset, we aim to match the activations on given…
Visualizing Transfer Learning
Róbert Szabó, Dániel Katona, Márton Csillag +2
We provide visualizations of individual neurons of a deep image recognition network during the temporal process of transfer learning. These visualizations qualitatively demonstrate…