[HTML][HTML] Towards practical reinforcement learning for tokamak magnetic control

BD Tracey, A Michi, Y Chervonyi, I Davies… - Fusion Engineering and …, 2024 - Elsevier
Reinforcement learning (RL) has shown promising results for real-time control systems,
including the domain of plasma magnetic control. However, there are still significant …

A Memory Management Method for DNN Inference for Aerospace Embedded Systems

S Li, F Wang, S Zhang, T Wang, Z Ma… - 2024 7th International …, 2024 - ieeexplore.ieee.org
Currently, deep neural networks (DNN) are widely used in aerospace field, however, due to
the embedded system in aerospace field, it is often difficult to support large-scale in-orbit …

[PDF][PDF] Enhancing Model Training Efficiency Through Fast Device Placement Algorithms

L Martinez, M Harris, E Anderson, A Thompson… - researchgate.net
Large-scale model training often faces challenges related to efficiency and resource
utilization. Optimizing the placement of model components across available hardware is …