32 citations · 133 across the 13 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022
Explaining, Evaluating and Enhancing Neural Networks' Learned Representations
Marco Bertolini, Djork-Arné Clevert, Floriane Montanari
Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing const…
cs.LG2022★ 7 cited
Unsupervised Learning of Group Invariant and Equivariant Representations
Robin Winter, Marco Bertolini, Tuan Le +2
Equivariant neural networks, whose hidden features transform according to representations of a group G acting on the data, exhibit training efficiency and an improved generalisatio…