Deep learning workload scheduling in gpu datacenters: A survey
Deep learning (DL) has demonstrated its remarkable success in a wide variety of fields. The
development of a DL model is a time-consuming and resource-intensive procedure. Hence …
development of a DL model is a time-consuming and resource-intensive procedure. Hence …
[HTML][HTML] Analysis of machine learning techniques for information classification in mobile applications
S Pérez Arteaga, AL Sandoval Orozco… - Applied Sciences, 2023 - mdpi.com
Due to the daily use of mobile technologies, we live in constant connection with the world
through the Internet. Technological innovations in smart devices have allowed us to carry …
through the Internet. Technological innovations in smart devices have allowed us to carry …
Differentiate quality of experience scheduling for deep learning inferences with docker containers in the cloud
Y Mao, W Yan, Y Song, Y Zeng, M Chen… - … on Cloud Computing, 2022 - ieeexplore.ieee.org
With the prevalence of big-data-driven applications, such as face recognition on
smartphones and tailored recommendations from Google Ads, we are on the road to a …
smartphones and tailored recommendations from Google Ads, we are on the road to a …
Computational estimation by scientific data mining with classical methods to automate learning strategies of scientists
AS Varde - ACM Transactions on Knowledge Discovery from Data …, 2022 - dl.acm.org
Experimental results are often plotted as 2-dimensional graphical plots (aka graphs) in
scientific domains depicting dependent versus independent variables to aid visual analysis …
scientific domains depicting dependent versus independent variables to aid visual analysis …
Many models at the edge: Scaling deep inference via model-level caching
Deep learning (DL) models are rapidly expanding in popularity in large part due to rapid
innovations in model accuracy, as well as companies' enthusiasm in integrating deep …
innovations in model accuracy, as well as companies' enthusiasm in integrating deep …
Layercake: Efficient Inference Serving with Cloud and Mobile Resources
Many mobile applications are now integrating deep learning models into their core
functionality. These functionalities have diverse latency requirements while demanding high …
functionality. These functionalities have diverse latency requirements while demanding high …
Resource-Efficient and Privacy-Preserving Edge for Augmented Reality
T Guo - Proceedings of the 2023 Workshop on Emerging …, 2023 - dl.acm.org
This position paper describes three directions to support network-enabled, interactive, DL-
powered augmented reality experience. The discussion is based on a generic sensing …
powered augmented reality experience. The discussion is based on a generic sensing …