[HTML][HTML] New universal sustainability metrics to assess edge intelligence

N Lenherr, R Pawlitzek, B Michel - Sustainable Computing: Informatics and …, 2021 - Elsevier
The single recent focus on deep learning accuracy ignores economic, and environmental
cost. Progress towards Green AI is hindered by lack of universal metrics that equally reward …

Edge computing using embedded webserver with mobile device for diagnosis and prediction of metastasis in histopathological images

A Johny, KN Madhusoodanan - International Journal of Computational …, 2021 - Springer
Diagnosis of different breast cancer stages using histopathology whole slide images is the
gold standard in grading the tissue metastasis. Traditional diagnosis involves labor intensive …

Edge computing for artificial intelligence

X Wang, Y Han, VCM Leung, D Niyato, X Yan… - Edge AI: Convergence …, 2020 - Springer
Extensive deployment of AI services, especially mobile AI, requires the support of edge
computing. This support is not just at the network architecture level, the design, adaptation …

Assessing Efficiency Benefits of Edge Intelligence

N Lenherr, R Pawlitzek, B Michel - Global IoT Summit, 2022 - Springer
The recent focus on deep learning accuracy ignored economic and environmental cost.
Introduction of Green AI is hampered by lack of metrics that balance rewards for accuracy …

Lightweight Approximation of Softmax Layer for On-Device Inference

I Vasyltsov, W Chang - Advances in Artificial Intelligence and Applied …, 2021 - Springer
In this paper we propose a method to approximate softmax layer for computer vision
applications, especially on the devices with limited hardware (HW) resources, such as …

[PDF][PDF] Sustainable Computing: Informatics and Systems

N Lenherr, R Pawlitzek, B Michel - seasonal-energymanager.com
The single recent focus on deep learning accuracy ignores economic, and environmental
cost. Progress towards Green AI is hindered by lack of universal metrics that equally reward …