Machine learning (ML) has seen tremendous advancements, but its environmental footprint remains a concern. Acknowledging the growing environmental impact of ML this paper …
Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 …
M Mattina - 2021 IEEE/ACM International Symposium on Low …, 2021 - ieeexplore.ieee.org
Deep learning inference at the edge continues to deliver state of the art results on real-world applications involving images, video, speech, and human activity. The workhorse behind …
Recent breakthroughs in Machine Learning (ML) applications, and especially in Deep Learning (DL), have made DL models a key component in almost every modern computing …
K Boubouh, R Basmadjian - Companion Proceedings of the 14th ACM …, 2023 - dl.acm.org
Energy efficiency is a critical concern for machine learning (ML) algorithms deployed in data centers. Recently, many works in the literature have focused on running ML algorithms on …
Today, deep learning optimization is primarily driven by research focused on achieving high inference accuracy and reducing latency. However, the energy efficiency aspect is often …
AE Eshratifar, M Pedram - 2020 IEEE 38th International …, 2020 - ieeexplore.ieee.org
We propose a learning algorithm to design a lightweight neural multiplexer that given the input and computational resource requirements, calls the model that will consume the …
Recent breakthrough technological progressions of powerful mobile computing resources such as low-cost mobile GPUs along with cutting-edge, open-source software architectures …
Today, deep learning optimization is primarily driven by research focused on achieving high inference accuracy and reducing latency. However, the energy efficiency aspect is often …