Designing rotationally invariant neural networks from PDEs and variational methods

Partial differential equation models and their associated variational energy formulations are often rotationally invariant by design. This ensures that a rotation of the input results in a corresponding rotation of the output, which is desirable in applications such as image analysis. Convolutional...

Descripción completa

Detalles Bibliográficos
Autores principales: Alt, Tobias, Schrader, Karl, Weickert, Joachim, Peter, Pascal, Augustin, Matthias
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2022
Materias:
Research
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9352643/
https://www.ncbi.nlm.nih.gov/pubmed/35941960
http://dx.doi.org/10.1007/s40687-022-00339-x

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9352643/
https://www.ncbi.nlm.nih.gov/pubmed/35941960
http://dx.doi.org/10.1007/s40687-022-00339-x

Ejemplares similares