Yüklüyor......

Machine learning in spectral domain

Deep neural networks are usually trained in the space of the nodes, by adjusting the weights of existing links via suitable optimization protocols. We here propose a radically new approach which anchors the learning process to reciprocal space. Specifically, the training acts on the spectral domain...

Ful tanımlama

Kaydedildi:
Detaylı Bibliyografya
Yayımlandı:Nat Commun
Asıl Yazarlar: Giambagli, Lorenzo, Buffoni, Lorenzo, Carletti, Timoteo, Nocentini, Walter, Fanelli, Duccio
Materyal Türü: Artigo
Dil:Inglês
Baskı/Yayın Bilgisi: Nature Publishing Group UK 2021
Konular:
Online Erişim:https://ncbi.nlm.nih.gov/pmc/articles/PMC7910623/
https://ncbi.nlm.nih.gov/pubmed/33637729
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1038/s41467-021-21481-0
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!