Machine learning in spectral domain

Theoretical aspects of automated learning from data involving deep neural networks have open questions. Here Giambagli et al. show that training the neural networks in the spectral domain of the network coupling matrices can reduce the amount of learning parameters and improve the pre-training proce...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti, Walter Nocentini, Duccio Fanelli
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/15ef900bcaf14e289d02281b5f925cbd
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!