Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
Katarzyna Filus, Kamil Faber, Roberto Corizzo +1
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catas…
cs.LG2026
Pulling Back the Curtain on Deep Networks
Maciej Satkiewicz, Roberto Corizzo, Marcin PietroÅ
In linear models, visualizing a weight vector naturally reveals the model's preferred input direction, but extending this intuition to deep networks via gradients or gradient ascen…
cs.LG2026
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
Maxwell Miller-Golub, Collin Coil, Kamil Faber +4
Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencie…