Towards energy-efficient deep learning: An overview of energy-efficient approaches along the deep learning lifecycle

V Mehlin, S Schacht, C Lanquillon - arxiv preprint arxiv:2303.01980, 2023 - arxiv.org
Deep Learning has enabled many advances in machine learning applications in the last few
years. However, since current Deep Learning algorithms require much energy for …

Language models are few-shot multilingual learners

GI Winata, A Madotto, Z Lin, R Liu, J Yosinski… - arxiv preprint arxiv …, 2021 - arxiv.org
General-purpose language models have demonstrated impressive capabilities, performing
on par with state-of-the-art approaches on a range of downstream natural language …

Cross-lingual cross-age group adaptation for low-resource elderly speech emotion recognition

S Cahyawijaya, H Lovenia, W Chung, R Frieske… - arxiv preprint arxiv …, 2023 - arxiv.org
Speech emotion recognition plays a crucial role in human-computer interactions. However,
most speech emotion recognition research is biased toward English-speaking adults, which …

[КНИГА][B] Efficient Design of Scalable Deep Neural Networks for Resource-Constrained Edge Devices

M Loni - 2022 - search.proquest.com
Abstract Deep Neural Networks (DNNs) are increasingly being processed on resource-
constrained edge nodes (computer nodes used in, eg, cyber-physical systems or at the edge …

[ОПИСАНИЕ][C] Optimization of AI Methods on Distributed-Memory Computing Architectures

D Coquelin - 2024 - Blekinge Institute of Technology