Neuron-by-Neuron Quantization for Efficient Low-Bit QNN Training

Quantized neural networks (QNNs) are widely used to achieve computationally efficient solutions to recognition problems. Overall, eight-bit QNNs have almost the same accuracy as full-precision networks, but working several times faster. However, the networks with lower quantization levels demonstrat...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Artem Sher, Anton Trusov, Elena Limonova, Dmitry Nikolaev, Vladimir V. Arlazarov
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2023-04-01
Edice:	Mathematics
Témata:	quantized neural network low-bit quantization layer-by-layer neuron-by-neuron training
On-line přístup:	https://www.mdpi.com/2227-7390/11/9/2112
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!