版权说明 操作指南
首页 > 成果 > 详情

Neural Network Panning: Screening the Optimal Sparse Network Before Training

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
会议论文
作者:
Kang, Xiatao;Li, Ping;Yao, Jiayi;Li, Chengxi
通讯作者:
Li, P
作者机构:
[Kang, Xiatao; Li, Ping; Yao, Jiayi] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.
[Li, Chengxi] Xidian Univ, Sch Comp, Xian, Peoples R China.
[Li, Ping] Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Peoples R China.
通讯机构:
[Li, P ] C
Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.
Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Peoples R China.
语种:
英文
关键词:
Deep learning;Reinforcement learning;Network pruning;Pruning before training
期刊:
Lecture Notes in Computer Science
ISSN:
0302-9743
年:
2023
卷:
13841
页码:
602-617
会议名称:
16th Asian Conference on Computer Vision (ACCV)
会议论文集名称:
Lecture Notes in Computer Science
会议时间:
DEC 04-08, 2022
会议地点:
Macao, PEOPLES R CHINA
会议主办单位:
[Kang, Xiatao;Li, Ping;Yao, Jiayi] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.^[Li, Chengxi] Xidian Univ, Sch Comp, Xian, Peoples R China.^[Li, Ping] Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha, Peoples R China.
主编:
Gall, J Chin, TJ Sato, I Chellappa, R Wang, L
出版地:
GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
出版者:
SPRINGER INTERNATIONAL PUBLISHING AG
ISBN:
978-3-031-26318-7; 978-3-031-26319-4
基金类别:
Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transp
机构署名:
本校为第一且通讯机构
院系归属:
计算机与通信工程学院
摘要:
Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses metrics to calculate weight scores for weight screening, and extends from the initial single-order pruning to iterative pruning. Through these works, we argue that network pruning can be summarized as an expressive force transfer process of weights, where the reserved weights will take on the expressive force from the removed ones for the purpose of maintaining t...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com