Dynamic Depth Learning in Stacked AutoEncoders

The effectiveness of deep learning models depends on their architecture and topology. Thus, it is essential to determine the optimal depth of the network. In this paper, we propose a novel approach to learn the optimal depth of a stacked AutoEncoder, called Dynamic Depth for Stacked AutoEncoders (DD...

Cijeli opis

Bibliografski detalji

Glavni autori:	Sarah Alfayez, Ouiem Bchir, Mohamed Maher Ben Ismail
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2023-10-01
Serija:	Applied Sciences
Teme:	dynamic depth learning stacked AutoEncoder unsupervised learning layer pruning
Online pristup:	https://www.mdpi.com/2076-3417/13/19/10994
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!