Standalone 16-bit Neural Network Training: Missing Study for Hardware-Limited Deep Learning Practitioners

v1v2v3v4v5 (latest)

Standalone 16-bit Neural Network Training: Missing Study for Hardware-Limited Deep Learning Practitioners

18 May 2023

Francois Rameau

Zhoulai Fu

ArXiv (abs)PDF HTML

Papers citing "Standalone 16-bit Neural Network Training: Missing Study for Hardware-Limited Deep Learning Practitioners"

7 / 7 papers shown

Title
Mixed Precision Training of Convolutional Neural Networks using Integer Operations Dipankar Das Naveen Mellempudi Dheevatsa Mudigere Dhiraj D. Kalamkar Sasikanth Avancha ... J. Corbal N. Shustrov R. Dubtsov Evarist Fomenko V. Pirogov MQ 63 154 0 03 Feb 2018
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference Benoit Jacob S. Kligys Bo Chen Menglong Zhu Matthew Tang Andrew G. Howard Hartwig Adam Dmitry Kalenichenko MQ 156 3,138 0 15 Dec 2017
Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks Hardik Sharma Jongse Park Naveen Suda Liangzhen Lai Benson Chau Joo-Young Kim Vikas Chandra H. Esmaeilzadeh MQ 61 491 0 05 Dec 2017
Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks Urs Koster T. Webb Xin Eric Wang Marcel Nassar Arjun K. Bansal ... Luke Hornof A. Khosrowshahi Carey Kloss Ruby J. Pai N. Rao MQ 47 261 0 06 Nov 2017
Identity Mappings in Deep Residual Networks Kaiming He Xinming Zhang Shaoqing Ren Jian Sun 354 10,192 0 16 Mar 2016
Fixed Point Quantization of Deep Convolutional Networks D. Lin S. Talathi V. Annapureddy MQ 95 816 0 19 Nov 2015
Learning both Weights and Connections for Efficient Neural Networks Song Han Jeff Pool J. Tran W. Dally CVBM 313 6,694 0 08 Jun 2015