Affichage des résultats 1 à 8 sur 8 au total
Mécanique statistique : 1 à 8 sur 8 au total
-
Thèse
Loris Felardos. Data-free Generation of Molecular Configurations with Normalizing Flows. Machine Learning [cs.LG]. Université Grenoble Alpes [2020-..], 2022. English. ⟨NNT : 2022GRALM026⟩. ⟨tel-04010123⟩
-
Pré-publication, Document de travail
Loris Felardos, Jérôme Hénin, Guillaume Charpiat. Designing losses for data-free training of normalizing flows on Boltzmann distributions. 2023. ⟨hal-03936982⟩
-
Article dans une revue
Nicolas Béreux, Aurélien Decelle, Cyril Furtlehner, Beatriz Seoane. Learning a Restricted Boltzmann Machine using biased Monte Carlo sampling. SciPost Physics, In press, 14, ⟨10.21468/SciPostPhys.14.3.032⟩. ⟨hal-03795598⟩
-
Article dans une revue
Aurélien Decelle, Tony Bonnaire, Nabila Aghanim. Cascade of phase transitions for multiscale clustering. Physical Review E , 2021, 103 (1), ⟨10.1103/PhysRevE.103.012105⟩. ⟨hal-03477663⟩
-
Article dans une revue
A Decelle, G Fissore, Cyril Furtlehner. Spectral Dynamics of Learning Restricted Boltzmann Machines. EPL - Europhysics Letters, 2017, 119, pp.60001. ⟨10.1209/0295-5075/119/60001⟩. ⟨hal-01652314⟩
-
Article dans une revue
Eugenio Lippiello, Giuseppe Petrillo, François Landes, Alberto Rosso. Fault Heterogeneity and the Connection between Aftershocks and Afterslip. Bulletin of the Seismological Society of America, 2019, 109 (3), pp.1156-1163. ⟨10.1785/0120180244⟩. ⟨hal-02156407⟩
-
Article dans une revue
Aurelien Decelle, Cyril Furtlehner. Gaussian-Spherical Restricted Boltzmann Machines. Journal of Physics A: Mathematical and Theoretical, 2020, ⟨10.1088/1751-8121/ab79f3⟩. ⟨hal-02420813⟩
-
Communication dans un congrès
Aurélien Decelle, Cyril Furtlehner, Beatriz Seoane. Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines. NeurIPS 2021, Dec 2021, Vancouver, United States. ⟨hal-03518796⟩