Training Multi-Bit Quantized and Binarized Networks with a Learnable Symmetric Quantizer

Quantizing weights and activations of deep neural networks is essential for deploying them in resource-constrained devices, or cloud platforms for at-scale services. While binarization is a special case of quantization, this extreme case often leads to several training difficulties, and necessitates...

Descripción completa

Detalles Bibliográficos

Autores principales:	Phuoc Pham, Jacob A. Abraham, Jaeyong Chung
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	IEEE 2021-01-01
Colección:	IEEE Access
Materias:	Learnable quantizer quantization binarization model compression machine learning neuromorphic computing
Acceso en línea:	https://ieeexplore.ieee.org/document/9383003/
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!