Magnitude and Similarity Based Variable Rate Filter Pruning for Efficient Convolution Neural Networks

The superior performance of the recent deep learning models comes at the cost of a significant increase in computational complexity, memory use, and power consumption. Filter pruning is one of the effective neural network compression techniques suitable for model deployment in modern low-power edge...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Deepak Ghimire, Seong-Heum Kim
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2022-12-01
Edice:	Applied Sciences
Témata:	convolution neural network filter pruning weight pruning loss-aware pruning pruning criterion
On-line přístup:	https://www.mdpi.com/2076-3417/13/1/316
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!