ComAI: Enabling lightweight, collaborative intelligence by retrofitting vision DNNs

• المؤلفون الرئيسيون: JAYARAJAH, Kasthuri, WANNIARACHCHIGE, Dhanuja, ABDELZAHER, Tarek, MISRA, Archan
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2022
• الموضوعات: Deep learning; runtime; machine vision; neural networks; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces; Software Engineering
• الوصول للمادة أونلاين: 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
• المؤسسة: Singapore Management University

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...