Improved Knowledge Distillationwith Dynamic Network Pruning

Deploying convolutional neural networks to mobile or embedded devices is often prohibited by limited memory and computational resources. This is particularly problematic for the most successful networks, which tend to be very large and require long inference times. Many alternative approaches have b...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Eren ŞENER, Emre AKBAŞ
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Gazi University 2022-09-01
Edice:	Gazi Üniversitesi Fen Bilimleri Dergisi
Témata:	knowledge distillation neural network compression image classification deep neural networks.
On-line přístup:	https://dergipark.org.tr/tr/pub/gujsc/issue/72673/1141648
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!