Automated deep learning: Neural architecture search is not the end
Deep learning (DL) has proven to be a highly effective approach for developing models in
diverse contexts, including visual perception, speech recognition, and machine translation …
diverse contexts, including visual perception, speech recognition, and machine translation …
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 …
years. However, since current Deep Learning algorithms require much energy for …
Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks
The most significant barrier to the advancement of Neural Architecture Search (NAS) is its
demand for large computational resources, which hinders scientifically sound empirical …
demand for large computational resources, which hinders scientifically sound empirical …
Survey on AI sustainability: emerging trends on learning algorithms and research challenges
Artificial Intelligence (AI) is a fast-growing research and development (R&D) discipline which
is attracting increasing attention because it promises to bring vast benefits for consumers …
is attracting increasing attention because it promises to bring vast benefits for consumers …
EA-HAS-bench: Energy-aware hyperparameter and architecture search benchmark
The energy consumption for training deep learning models is increasing at an alarming rate
due to the growth of training data and model scale, resulting in a negative impact on carbon …
due to the growth of training data and model scale, resulting in a negative impact on carbon …
Advancing green computer vision: principles and practices for sustainable development for real-time computer vision applications
MAM Kramer, PM Roth - … time Processing of Image, Depth, and …, 2024 - spiedigitallibrary.org
Recent algorithmic developments, specifically in deep learning, have propelled computer
vision forward for practical applications. However, the high computational complexity and …
vision forward for practical applications. However, the high computational complexity and …
Federated Transfer Learning for Energy Efficient Privacy-preserving Medical Image Classification
MS Ahmed, S Giordano - 2022 IEEE International Conference …, 2022 - ieeexplore.ieee.org
The deep convolutional neural networks are widely used in medical image classification
tasks. In some cases, they have outperformed physicians and achieved significant results …
tasks. In some cases, they have outperformed physicians and achieved significant results …
Life Cycle Assessment and Model Optimization for Sustainable Energy Cross-Border E-Commerce
H Liu, R Cui - EAI Endorsed Transactions on Energy Web, 2024 - publications.eai.eu
INTRODUCTION: In an in-depth study of the application of sustainable energy in cross-
border e-commerce, a comprehensive assessment and model optimization of its life cycle …
border e-commerce, a comprehensive assessment and model optimization of its life cycle …
Energy-efficient real-time computer vision applications in practice
MAM Kramer, PM Roth - … time Processing of Image, Depth, and …, 2024 - spiedigitallibrary.org
For many practical applications, we face the problem that computer vision systems must be
installed in the wild, without or with a limited permanent power supply. Therefore …
installed in the wild, without or with a limited permanent power supply. Therefore …