From the 2 of 5.3k papers with an AI index.
29.3k citations
- Centre National de la Recherche ScientifiqueFR1.2k papers
- Sorbonne UniversitéFR664 papers
- Université Paris-SaclayFR657 papers
- Université Paris CitéFR617 papers
- University of ZurichCH607 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di BolognaIT606 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR603 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di Roma IIT596 papers
- Aix-Marseille UniversitéFR590 papers
- European Organization for Nuclear ResearchCH586 papers
- University of OxfordGB581 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di GenovaIT579 papers
42 papers · 2 filters
Distributed Adaptive Learning Under Communication Constraints
Marco Carpentiero, Vincenzo Matta, Ali H. Sayed
This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimizat…
Correlation inference attacks against machine learning models
Ana-Maria Creţu, Florent Guépin, Yves-Alexandre de Montjoye
Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks,…
ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groups
Hugo Aguettaz, Erik J. Bekkers, Michaël Defferrard
We introduce ChebLieNet, a group-equivariant method on (anisotropic) manifolds. Surfing on the success of graph- and group-based neural networks, we take advantage of the recent de…
Multi-Centroid Hyperdimensional Computing Approach for Epileptic Seizure Detection
Una Pale, Tomas Teijeiro, David Atienza
Long-term monitoring of patients with epilepsy presents a challenging problem from the engineering perspective of real-time detection and wearable devices design. It requires new s…
Regularization by Misclassification in ReLU Neural Networks
Elisabetta Cornacchia, Jan Hązła, Ido Nachum +1
We study the implicit bias of ReLU neural networks trained by a variant of SGD where at each step, the label is changed with probability to a random label (label smoothing bein…
Understanding Layer-wise Contributions in Deep Neural Networks through Spectral Analysis
Yatin Dandi, Arthur Jacot
Spectral analysis is a powerful tool, decomposing any function into simpler parts. In machine learning, Mercer's theorem generalizes this idea, providing for any kernel and input d…