A 1.23μJ/Inference, All-Digital Shuffle-Type Group-CNN Accelerator in 28nm CMOS With 85.8% Accuracy on CIFAR-10
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Circuits and Systems II: Express Briefs"
DOI: 10.1109/tcsii.2022.3197827
Abstract: To achieve high energy efficiency for edge processing, we implement an all-digital shuffle-type group CNN accelerator with binary weights, which is the first reported shuffle-type GCNN accelerator in CMOS as far as we know. Cross-level… read more here.
Keywords: shuffle type; cmos; accelerator; digital shuffle ... See more keywords