H Hua, Y Li, T Wang, N Dong, W Li, J Cao - ACM Computing Surveys, 2023 - dl.acm.org
… While heuristicbased algorithms and data mining (DM) [7] have both played an important role in AI solutions to IoT in the past decades, we mainly focus on machinelearning (ML), a …
M Verhelst, B Murmann - NANO-CHIPS 2030: On-Chip AI for an Efficient …, 2020 - Springer
… trends for low-energy machinelearning inference and training at the edge. It covers dataflow… evolution has already resulted in a very broad landscape of customized machinelearning …
… and storage resources to the edge of the network, involving a … of deploying machinelearning (ML) at the network edge to … developing and implementing machinelearning algorithms that …
… an edge network. This article investigates the application of machinelearning techniques for in-network caching in edge … Thirdly, edge networks evolve with dynamic user associations, …
… machinelearning, ie evolutionary computation techniques for major machinelearning tasks … , computer vision, deep learning, transfer learning, and ensemble learning. The paper also …
… Edge computing and machinelearning will enable … learning is a common way of training machinelearning algorithms that can be later used in the inference stage on IoT and other edge …
CP Filho, E Marques Jr, V Chang, L Dos Santos… - Sensors, 2022 - mdpi.com
Distributed edge intelligence is a disruptive research area that enables the … of machine learning and deep learning (ML/DL) algorithms close to where data are generated. Since edge …
… MachineLearning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the …
W Toussaint, AY Ding - … Conference on Cognitive Machine …, 2020 - ieeexplore.ieee.org
… Equally, if applications are dynamic and evolve over time, machinelearning systems can use new data to discover patterns and update their predictions, thus adapting with the …