CDFKD-MFS: Collaborative Data-Free Knowledge Distillation via Multi-Level Feature Sharing
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2022.3192663
Abstract: Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for compression, its requirement… read more here.
Keywords: data free; feature sharing; level feature; multi level ... See more keywords
Visualizing complex feature interactions and feature sharing in genomic deep neural networks
Sign Up to like & getrecommendations! Published in 2019 at "BMC Bioinformatics"
DOI: 10.1186/s12859-019-2957-4
Abstract: Visualization tools for deep learning models typically focus on discovering key input features without considering how such low level features are combined in intermediate layers to make decisions. Moreover, many of these methods examine a… read more here.
Keywords: feature sharing; deep neural; neural networks; feature ... See more keywords