Multi-task zipping via layer-wise neuron sharing
Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks on-device. Yet the complexity of these neural networks needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory....
Saved in:
Main Authors: | HE, Xiaoxi, ZHOU, Zimu, THIELE, Lothar |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2018
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/4554 https://ink.library.smu.edu.sg/context/sis_research/article/5557/viewcontent/neurips18_he.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
On-device deep multi-task inference via multi-task zipping
by: HE, Xiaoxi, et al.
Published: (2023) -
MapTransfer: Urban air quality map generation for downscaled sensor deployments
by: CHENG, Yun, et al.
Published: (2020) -
Enhancing multi-hop sensor calibration with uncertainty estimates
by: MAAG, Balz, et al.
Published: (2019) -
ICT: In-field calibration transfer for air quality sensor deployments
by: CHENG, Yun, et al.
Published: (2019) -
W-Air: Enabling personal air pollution monitoring on wearables
by: MAAG, Balz, et al.
Published: (2018)