The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep convolutional networks represent an important special case of these conditions, though weight sharing is not the main reason for their exponential advantage. Implications of a few key theorems are discussed, together with new results, open problems and conjectures.
Titolo: | Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review | |
Autori: | ||
Data di pubblicazione: | 2017 | |
Rivista: | ||
Handle: | http://hdl.handle.net/11567/888539 | |
Appare nelle tipologie: | 01.01 - Articolo su rivista |
File in questo prodotto:
File | Descrizione | Tipologia | |
---|---|---|---|
11567-888539.pdf | Articolo principale | Documento in versione editoriale | Open Access Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.