Multi-Resolution Model Compression for Deep Neural Networks: A Variational Bayesian Approach-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Multi-Resolution Model Compression for Deep Neural Networks: A Variational Bayesian Approach

Published:2024 Issue: Volume:72 Page:1944-1959
ISSN:1053-587X
Container-title:IEEE Transactions on Signal Processing
language:
Short-container-title:IEEE Trans. Signal Process.

Author:

Xia Chengyu¹^ORCID,Guo Huayan²^ORCID,Ma Haoyu¹^ORCID,Tsang Danny H. K.³^ORCID,Lau Vincent K. N.¹^ORCID

Affiliation:

1. Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China

2. The Hong Kong University of Science and Technology, Shenzhen Research Institute, Shenzhen, China

3. Internet of Things Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China

Funder

Hong Kong Research Grants Council under the Areas of Excellence Scheme

Hong Kong Research Grants Council

Guangdong Provincial Project

Guangzhou Municipal Science and Technology Project

Guangdong Provincial Key Laboratory of Integrated Communications, Sensing and Computation for Ubiquitous Internet of Things

National Foreign Expert Project

National Natural Science Foundation of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/78/10347386/10485207.pdf?arnumber=10485207

Reference48 articles.

1. An overview of neural network compression;Neill,2020

2. Optimal brain damage;LeCun,1989

3. Second order derivatives for network pruning: Optimal brain surgeon;Hassibi,1992

4. Removal of hidden units and weights for back propagation networks

5. Snip: Single-shot network pruning based on connection sensitivity;Lee,2018

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP