search

dorimedini / robustness_properties

GLOBIGLOBIGLOBI
0 stars 0 forks source link

Experiment with regularization #41

Open noamloya opened 5 years ago

noamloya commented 5 years ago

After adding regularization to trainer, go over all datasets and experiment with every type of regularization, and check the robustness effect when training with it (Train -> Reinitialize layers -> See the effect on accuracy). What happens to the critical\robust effect in this setting? Are the robust layers the same? Does the criticalness spread\diffuse over all layers?

dorimedini commented 5 years ago

@noamloya could you walk me through how this experiment works...? I want to take this ticket but I don't know what exactly it is I'm trying to measure and what phenomenon I'm looking for