Close

Presentation

EBSP: Evolving Bit Sparsity Patterns for Hardware-Friendly Inference of Quantized Deep Neural Networks
TimeTuesday, July 12th3:54pm - 4:18pm PDT
Location3002, Level 3
Event Type
Research Manuscript
Keywords
AI/ML Design: Circuits and Architecture
Topics
Design
DescriptionDue to the huge model size and computation amount, to support efficient implementations of DNN inference on edge-computing platforms