Web: http://arxiv.org/abs/2201.11651

Jan. 28, 2022, 2:11 a.m. | Shurui Li, Puneet Gupta

cs.LG updates on arXiv.org arxiv.org

Applications of neural networks on edge systems have proliferated in recent
years but the ever-increasing model size makes neural networks not able to
deploy on resource-constrained microcontrollers efficiently. We propose
bit-serial weight pools, an end-to-end framework that includes network
compression and acceleration of arbitrary sub-byte precision. The framework can
achieve up to 8x compression compared to 8-bit networks by sharing a pool of
weights across the entire network. We further propose a bit-serial lookup based
software implementation that allows runtime-bitwidth …

arxiv compression networks neural neural networks precision processors

More from arxiv.org / cs.LG updates on arXiv.org

Senior Data Engineer

@ DAZN | Hammersmith, London, United Kingdom

Sr. Data Engineer, Growth

@ Netflix | Remote, United States

Data Engineer - Remote

@ Craft | Wrocław, Lower Silesian Voivodeship, Poland

Manager, Operations Data Science

@ Binance.US | Vancouver

Senior Machine Learning Researcher for Copilot

@ GitHub | Remote - Europe

Sr. Marketing Data Analyst

@ HoneyBook | San Francisco, CA