Close

Presentation

Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
DescriptionIn this paper, we propose a multi-dimensional model pruning framework to comprehensively reduce the computational cost of convolutional neural networks (CNNs), facilitating the deployment of advanced CNNs onto resource-constrained embedded devices.
Event Type
Research Manuscript
TimeThursday, July 13th4:25pm - 4:40pm PDT
Location3006, 3rd Floor
Topics
Embedded Systems
RISC-V
Keywords
Embedded Software