物联网学报2024，Vol.8Issue(4)：1-13,13.DOI:10.11959/j.issn.2096-3750.2024.00448
物联网中模型剪枝技术:现状、方法和展望
Model pruning techniques in the Internet of things:state of the art,methods and perspectives
摘要
Abstract
In the context of the rapid development of Internet of things(IoT)technology,IoT devices faced challenges in running complex artificial intelligence(AI)algorithms,especially deep learning models,due to the limitations of comput-ing power,storage space,communication bandwidth,and battery life.Model pruning technology could effectively reduce computation and storage requirements by reducing redundant parameters in neural networks without impairing the perfor-mance of AI models.This technique was extremely suitable for optimising AI models deployed on IoT devices.Firstly,two typical model pruning techniques-structured pruning and unstructured pruning,which were currently popular and suit-able for different application scenarios,were reviewed.Secondly,the diverse applications of these methods in IoT envi-ronments were analysed in detail.Finally,the limitations of the current model pruning were discussed in detail in the light of the latest research results,and the future development direction of model pruning methods in IoT was outlooked.关键词
物联网/资源限制/模型剪枝/人工智能/深度学习Key words
IoT/resource constraints/model pruning/AI/deep learning分类
信息技术与安全科学引用本文复制引用
赵军辉,李怀城,王东明,李佳珉,周一青,束锋..物联网中模型剪枝技术:现状、方法和展望[J].物联网学报,2024,8(4):1-13,13.基金项目
国家自然科学基金资助项目(No.U2001213) （No.U2001213）
国家重点研发计划(No.2020YFB1807204)The National Natural Science Foundation of China(No.U2001213),The National Key Research and Develop-ment Program of China(No.2020YFB1807204) （No.2020YFB1807204）
