Advancements in Accelerating Deep Neural Network Inference on AIoT Devices: A Survey

• Published in: IEEE transactions on sustainable computing Vol. 9; no. 6; pp. 830 - 847
• Main Authors: Cheng, Long, Gu, Yan, Liu, Qingzhi, Yang, Lei, Liu, Cheng, Wang, Ying
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.11.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; AIoT devices; Artificial intelligence; Artificial neural networks; Co-design; Computational modeling; Computing time; Data models; Devices; DNN inference; Hardware; Inference; Internet of Things; model compression; Neural networks; Optimization; parallel computing; Parallel processing; performance optimization; survey
• ISSN: 2377-3782; 2377-3790
• DOI: 10.1109/TSUSC.2024.3353176

The amalgamation of artificial intelligence with Internet of Things (AIoT) devices have seen a rapid surge in growth, largely due to the effective implementation of deep neural network (DNN) models across various domains. However, the deployment of DNNs on such devices comes with its own set of chal...