Template-Type: ReDIF-Article 1.0
Author-Name: Ziyi Gong
Author-Email:  804250678@qq.com
Author-Workplace-Name: Department of Computer Sciences and Engineering, Hunan University of Science and Technology, Xiangtan, Hunan, China
Author-Name: Huifu Zhang
Author-Workplace-Name: Department of Computer Sciences and Engineering, Hunan University of Science and Technology, Xiangtan, Hunan, China
Author-Name:  Hao Yang
Author-Workplace-Name: Department of Computer Sciences and Engineering, Hunan University of Science and Technology, Xiangtan, Hunan, China
Author-Name:  Fangjun Liu
Author-Workplace-Name: Department of Computer Sciences and Engineering, Hunan University of Science and Technology, Xiangtan, Hunan, China
Author-Name:  Fan Luo
Author-Workplace-Name: Department of Computer Sciences and Engineering, Hunan University of Science and Technology, Xiangtan, Hunan, China
Title:  A Review of Neural Network Lightweighting Techniques
Abstract:  The application of portable devices based on deep learning has become increasingly widespread, which has made the deployment of complex neural networks on embedded devices a hot research topic. Neural network lightweighting is one of the key technologies for applying neural networks to embedded devices. This paper elaborates and analyzes neural network lightweighting techniques from two aspects: model pruning and network structure design. For model pruning, a comparison of methods from different periods is conducted, highlighting their advantages and limitations. Regarding network structure design, the principles of four classical lightweight network designs are described from a mathematical perspective, and the latest optimization methods for these networks are reviewed. Finally, potential research directions for lightweight neural network pruning and structure design optimization are discussed.
Keywords: Lightweighting Techniques for Neural Networks, Model Pruning, Network Structure Design, Convolutional Structure Optimization
Journal: Innovation & Technology Advances
Pages: 1-24
Volume: 1
Issue: 2
Year: 2023
Month: ‌December
DOI: 10.61187/ita.v1i2.36
File-URL: https://bergersci.com/index.php/jta/article/view/36/23
File-Format: Application/pdf
File-URL: https://bergersci.com/index.php/jta/article/view/36
File-Format: text/html
Handle: RePEc:cwi:itadva:v:1:y:2023:i:2:p:1-24