ComAI: Enabling lightweight, collaborative intelligence by retrofitting vision DNNs
While Deep Neural Network (DNN) models have transformed machine vision capabilities, their extremely high computational complexity and model sizes present a formidable deployment roadblock for AIoT applications. We show that the complexity-vs-accuracy-vs-communication tradeoffs for such DNN models c...
Saved in:
Main Authors: | JAYARAJAH, Kasthuri, WANNIARACHCHIGE, Dhanuja, ABDELZAHER, Tarek, MISRA, Archan |
---|---|
格式: | text |
語言: | English |
出版: |
Institutional Knowledge at Singapore Management University
2022
|
主題: | |
在線閱讀: | https://ink.library.smu.edu.sg/sis_research/7164 https://ink.library.smu.edu.sg/context/sis_research/article/8168/viewcontent/infocom22_collabml_cameraready.pdf |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Enabling collaborative video sensing at the edge through convolutional sharing
由: KASTHURI JAYARAJAH,, et al.
出版: (2020) -
HSCoNAS : hardware-software co-design of efficient DNNs via neural architecture search
由: Luo, Xiangzhong, et al.
出版: (2022) -
Runtime binary analysis for security
由: SARAVANAN SINNADURAI S/O GUNACHILAN
出版: (2010) -
Five challenges in cloud-enabled intelligence and control
由: ABDELZAHER, Tarek, et al.
出版: (2020) -
Ensuring Faultless Communication Behaviour in A Commercial Cloud
由: Umarov, Timur, et al.
出版: (2015)