Compression of Deep Neural Networks with Structured Sparse Ternary Coding
Sign Up to like & getrecommendations! Published in 2019 at "Journal of Signal Processing Systems"
DOI: 10.1007/s11265-018-1418-z
Abstract: Deep neural networks (DNNs) contain large number of weights, and usually require many off-chip memory accesses for inference. Weight size compression is a major requirement for on-chip memory based implementation of DNNs, which not only… read more here.
Keywords: compression deep; deep neural; neural networks; networks structured ... See more keywords