Asosiy kontentga oʻtish
Maqola

Geometric Deep Learning: Going beyond Euclidean data

Michael M. BronsteinTel Aviv University, IsraelJoan BrunaNYU, Courant InstituteYann LeCunFacebookArthur SzlamMeta (United States)Pierre VandergheynstEcole Polytechnique Federale de Lausanne, Switzerland
2017en
ABI

Annotatsiya

Geometric deep learning is an umbrella term for emerging techniques attempting to generalize (structured) deep neural models to non-Euclidean domains, such as graphs and manifolds. The purpose of this article is to overview different examples of geometric deep-learning problems and present available solutions, key difficulties, applications, and future research directions in this nascent field.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar

7 ta iqtibos0 ta foydalanilgan manba