2 citations · 2 across the 2 of their papers we have counts for
3 papers
cs.LG2022
Towards understanding deep learning with the natural clustering prior
Simon Carbonnelle
The prior knowledge (a.k.a. priors) integrated into the design of a machine learning system strongly influences its generalization abilities. In the specific context of deep learni…
cs.LG2021★ 2 cited
Intraclass clustering: an implicit learning ability that regularizes DNNs
Carbonnelle Simon, Christophe De Vleeschouwer
Several works have shown that the regularization mechanisms underlying deep neural networks' generalization performances are still poorly understood. In this paper, we hypothesize…
cs.LG2018
Layer rotation: a surprisingly powerful indicator of generalization in deep networks?
Simon Carbonnelle, Christophe De Vleeschouwer
Our work presents extensive empirical evidence that layer rotation, i.e. the evolution across training of the cosine distance between each layer's weight vector and its initializat…