134 citations · 306 across the 23 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024★ 1 cited
Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition
Kenzo Clauw, Sebastiano Stramaglia, Daniele Marinazzo
This paper studies emergent phenomena in neural networks by focusing on grokking where models suddenly generalize after delayed memorization. To understand this phase transition, w…
cs.LG2022★ 3 cited
Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance
Kenzo Clauw, Sebastiano Stramaglia, Daniele Marinazzo
Quantifying which neurons are important with respect to the classification decision of a trained neural network is essential for understanding their inner workings. Previous work p…