Загрузка...

Equivariant neural networks for inverse problems

In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of research into incorporating other symmetries into deep learning methods, in the f...

Полное описание

Сохранить в:
Библиографические подробности
Опубликовано в: :Inverse Probl
Главные авторы: Celledoni, Elena, Ehrhardt, Matthias J, Etmann, Christian, Owren, Brynjulf, Schönlieb, Carola-Bibiane, Sherry, Ferdia
Формат: Artigo
Язык:Inglês
Опубликовано: IOP Publishing 2021
Предметы:
Online-ссылка:https://ncbi.nlm.nih.gov/pmc/articles/PMC8317019/
https://ncbi.nlm.nih.gov/pubmed/34334869
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1088/1361-6420/ac104f
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!