.png){kind=icon}
Return
Enabling Resource-Efficient Edge Intelligence with Compressive Sensing-Based Deep Learning
.png){kind=icon}
PRE
AI
DOI：10.1145/3528416.3530230.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Billions of sensor-enabled computing devices open tremendous opportunities for AI-powered context-aware services. Yet, democratizing AI so that heterogeneous devices can enjoy deep learning (DL) revolution requires significant reduction in computing and energy burden posed by DL models. Inspired by the concept of compressive sensing (CS), and guided by the observation that reduced sampling rates often suffice for successful classification, we devise an adaptive CS-DL pipeline. Our approach dynamically adjusts the sensing rate according to input properties and performs classification through an input-flexible DL model, demonstrating classification accuracy rates on par with uncompressed models while using up to 46% less battery energy.
Keywords:
neural networks
compressive sensing
human activity recognition
Journal
P
IF:
0
Papers:
1.8K
Citations:
0
Organization
Cited Papers
ShareSaveShareSaveMultiple Autism-Linked Genes Mediate Synapse Elimination via Proteasomal Degradation of a Synaptic Scaffold PSD-95.png)
Cell
OAAI
CellIF0
OAAIShareSaveShareSave
ShareSave
View more