English

Dual Precision Deep Neural Network

Machine Learning 2024-05-14 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.2009.02191,
  title  = {Dual Precision Deep Neural Network},
  author = {Jae Hyun Park and Ji Sub Choi and Jong Hwan Ko},
  journal= {arXiv preprint arXiv:2009.02191},
  year   = {2024}
}

Comments

5 pages, 4 figures, 2 tables

R2 v1 2026-06-23T18:19:06.599Z