Andrew Nelson — accepted AI-conference papers

2021

CompROS: A composable ROS2 based architecture for real-time embedded robotic development

Saeid Dehnavi, Martijn Koedam, Andrew Nelson, Dip Goswami, Kees Goossens

IROS 2021poster

Robot Operating System (ROS) is a de-facto standard robot middleware in many academic and industrial use cases. However, utilizing ROS/ROS2 in safety-critical embedded applications with real-time requirement is challenging because of C1) Non-real-time underlying hardware, C2) No control on the host…

Cited by 13 Source ↗Scholar ↗

2021

DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

Wei Sun, Aojun Zhou, Sander Stuijk, Rob G. J. Wijnhoven, Andrew Nelson, Hongsheng Li +1

NeurIPS 2021poster

Neural pruning is a widely-used compression technique for Deep Neural Networks (DNNs). Recent innovations in Hardware Architectures (e.g. Nvidia Ampere Sparse Tensor Core) and N:M fine-grained Sparse Neural Network algorithms (i.e. every M-weights contains N non-zero values) reveal a promising resea…

Cited by 70 Source ↗PDF ↗code ↗Scholar ↗