.png){kind=icon}
Return
Intermittent-Aware Neural Network Pruning
.png){kind=icon}
PRE
AI
DOI：10.1109/DAC56929.2023.10247825.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep neural network inference on energy harvesting tiny devices has emerged as a solution for sustainable edge intelligence. However, compact models optimized for continuously-powered systems may become suboptimal when deployed on intermittently-powered systems. This paper presents the pruning criterion, pruning strategy, and prototype implementation of iPrune, the first framework which introduces intermittency into neural network pruning to produce compact models adaptable to intermittent systems. The pruned models are deployed and evaluated on a Texas Instruments device with various power strengths and TinyML applications. Compared to an energy-aware pruning framework, iPrune can speed up intermittent inference by 1.1 to 2 times while achieving comparable model accuracy.
Keywords:
Neural network pruning
deep learning
intermittent computing
battery-less devices
Journal
A
IF:
0
Papers:
5
Citations:
0
Organization
Cited Papers
Analysis of chemical polymerization between functionalized MWCNT and poly(furfuryl alcohol) composite.png)
Polímeros
OAAI
PolímerosIF0
OAAIShareSaveShareSaveShareSaveFactors Associated with Variations in Population HIV Prevalence across West Africa: Findings from an Ecological AnalysisPLOS ONEOAAI
PLOS ONEIF0
OAAIShareSaveEfficient Processing of Deep Neural Networks: A Tutorial and SurveyPROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAIShareSave
View more