Mixed-Precision Neural Architecture Search and Dynamic Split Point Selection for Split Computing

Split computing (SC) is an emerging technique to perform the inference task of deep neural network (DNN) models using both mobile devices and cloud/edge servers in a hybrid manner. To improve the end-to-end inference time over the network, SC splits a single DNN model into a head model and a tail mo...

Descripción completa

Detalles Bibliográficos

Autores principales:	Naoki Nagamatsu, Kenshiro Ise, Yuko Hara
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	IEEE 2024-01-01
Colección:	IEEE Access
Materias:	Deep neural networks split computing mixed-precision quantization neural architecture search
Acceso en línea:	https://ieeexplore.ieee.org/document/10669028/
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!