ClassyNet: Class-Aware Early Exit Neural Networks for Edge Devices

M Ayyat, T Nadeem, B Krawczyk - IEEE Internet of Things …, 2023 - ieeexplore.ieee.org
Edge-based and IoT devices have seen phenomenal growth in recent years, driven by the
surge in demand for emerging applications that leverage machine learning models, such as …

Energy-Efficient Inference With Software-Hardware Co-Design for Sustainable Artificial Intelligence of Things

S Dai, Z Luo, W Luo, S Wang, C Dai… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
The emerging field of artificial intelligence of things (AIoT) is propelled by the remarkable
success of deep learning and hardware evolution, which has a significant impact on our …

Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning

F Szatkowski, F Yang, B Twardowski… - arXiv preprint arXiv …, 2024 - arxiv.org
Driven by the demand for energy-efficient employment of deep neural networks, early-exit
methods have experienced a notable increase in research attention. These strategies allow …

Zero-Waste Machine Learning

T Trzcinski, B Twardowski, B Zieliński… - ECAI 2024, 2024 - ebooks.iospress.nl
Today, both science and industry rely heavily on machine learning models, predominantly
artificial neural networks, that become increasingly complex and demand more computing …

Joint or Disjoint: Mixing Training Regimes for Early-Exit Models

B Krzepkowski, M Michaluk, F Szarwacki… - arXiv preprint arXiv …, 2024 - arxiv.org
Early exits are an important efficiency mechanism integrated into deep neural networks that
allows for the termination of the network's forward pass before processing through all its …