Dual Precision Deep Neural Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Park, Jae Hyun, Choi, Ji Sub, Ko, Jong Hwan
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913346768338944
author Park, Jae Hyun
Choi, Ji Sub
Ko, Jong Hwan
author_facet Park, Jae Hyun
Choi, Ji Sub
Ko, Jong Hwan
contents On-line Precision scalability of the deep neural networks(DNNs) is a critical feature to support accuracy and complexity trade-off during the DNN inference. In this paper, we propose dual-precision DNN that includes two different precision modes in a single model, thereby supporting an on-line precision switch without re-training. The proposed two-phase training process optimizes both low- and high-precision modes.
format Preprint
id arxiv_https___arxiv_org_abs_2009_02191
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Dual Precision Deep Neural Network
Park, Jae Hyun
Choi, Ji Sub
Ko, Jong Hwan
Machine Learning
Computer Vision and Pattern Recognition
On-line Precision scalability of the deep neural networks(DNNs) is a critical feature to support accuracy and complexity trade-off during the DNN inference. In this paper, we propose dual-precision DNN that includes two different precision modes in a single model, thereby supporting an on-line precision switch without re-training. The proposed two-phase training process optimizes both low- and high-precision modes.
title Dual Precision Deep Neural Network
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2009.02191