NITI: Training Integer Neural Networks Using Integer-Only Arithmetic-Reference-Cited by-同舟云学术

NITI: Training Integer Neural Networks Using Integer-Only Arithmetic

Author:

Wang Maolin¹^ORCID,Rasoulinezhad Seyedramin²^ORCID,Leong Philip H. W.²^ORCID,So Hayden K.-H.³^ORCID

Affiliation:

1. ACCESS – AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Hong Kong, China

2. School of Electrical and Information Engineering, The University of Sydney, Camperdown, NSW, Australia

3. Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong

Funder

Innovation Award

ACCESS – AI Chip Center for Emerging Smart Systems

Innovation and Technology Fund

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computational Theory and Mathematics,Hardware and Architecture,Signal Processing

Link

Reference41 articles.

1. TensorFlow: Large-scale machine learning on heterogeneous systems;abadi,2015

2. PyTorch: An imperative style, high-performance deep learning library;paszke;Proc Adv Neural Informat Process Syst,2019

3. Understanding the difficulty of training deep feedforward neural networks;glorot;Proc 13th Int Conf Artif Intell Statist,2010

Cited by 16 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. On-Device Continual Learning With STT-Assisted-SOT MRAM-Based In-Memory Computing;IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems;2024-08

3. Machine Learning Training on Encrypted Data with TFHE;Proceedings of the 10th ACM International Workshop on Security and Privacy Analytics;2024-06-19

5. SoCFlow: Efficient and Scalable DNN Training on SoC-Clustered Edge Servers;Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1;2024-04-17