A Review on the emerging technology of TinyML

被引:4
|
作者
Tsoukas, Vasileios [1 ,2 ]
Gkogkidis, Anargyros [1 ,2 ]
Boumpa, Eleni [1 ,2 ]
Kakarountas, Athanasios [1 ,2 ]
机构
[1] Univ Thessaly, Sch Sci, Comp Sci & Biomed Informat, Lamia, Central Greece, Greece
[2] Univ Thessaly, Sch Sci, Intelligent Syst Lab, Lamia, Central Greece, Greece
关键词
TinyML; machine learning; neural networks; edge AI; resource-constrained intelligence; microcontrollers; constrained hardware; optimization; NEURAL-NETWORKS; INTERNET; EDGE; ALGORITHMS; ACCELERATOR; BLOCKCHAINS; AI;
D O I
10.1145/3661820
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Tiny Machine Learning (TinyML) is an emerging technology proposed by the scientific community for developing autonomous and secure devices that can gather, process, and provide results without transferring data to external entities. The technology aims to democratize AI by making it available to more sectors and contribute to the digital revolution of intelligent devices. In this work, a classification of the most common optimization techniques for Neural Network compression is conducted. Additionally, a review of the development boards and TinyML software is presented. Furthermore, the work provides educational resources, a classification of the technology applications, and future directions and concludes with the challenges and considerations.
引用
收藏
页数:37
相关论文
共 50 条