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...

Descrición completa

Detalles Bibliográficos

Principais autores:	Artem Sher, Anton Trusov, Elena Limonova, Dmitry Nikolaev, Vladimir V. Arlazarov
Formato:	Artigo
Idioma:	Inglês
Publicado:	MDPI AG 2023-04-01
Series:	Mathematics
Assuntos:	quantized neural network low-bit quantization layer-by-layer neuron-by-neuron training
Acceso en liña:	https://www.mdpi.com/2227-7390/11/9/2112
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!