'Place-cell' emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space - Archive ouverte HAL
Article Dans Une Revue Journal of Physics A: Mathematical and Theoretical Année : 2020

'Place-cell' emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space

Fichier principal
Vignette du fichier
main.pdf (1.85 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02425376 , version 1 (30-12-2019)

Identifiants

Citer

Moshir Harsh, Jérôme Tubiana, Simona Cocco, Rémi Monasson. 'Place-cell' emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space. Journal of Physics A: Mathematical and Theoretical, 2020, 53 (17), pp.174002. ⟨10.1088/1751-8121/ab7d00⟩. ⟨hal-02425376⟩
100 Consultations
51 Téléchargements

Altmetric

Partager

More