Fast Exploration Of Weight Sharing Opportunities For Cnn Compression
ASecurity
**arXiv ID:** 2102.01345 **Authors:** Etienne Dupuis, David Novo, Ian O'Connor, Alberto Bosio **Published:** 2021-02-02T06:45:56Z **Abstract:** The computational workload involved in Convolutional Neural Networks (CNNs) is typically out of reach for low-power embedded devices. There are a large number of approximation techniques to address this problem. These methods have hyper-parameters that need to be optimized for each CNNs using design space exploration (DSE). The goal of this work is to...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Fast Exploration Of Weight Sharing Opportunities For Cnn Compression?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-fast-exploration-of-weight-sharing-opportunities-f)
# Fast Exploration of Weight Sharing Opportunities for CNN Compression
**arXiv ID:** 2102.01345
**Authors:** Etienne Dupuis, David Novo, Ian O'Connor, Alberto Bosio
**Published:** 2021-02-02T06:45:56Z
**Abstract:**
The computational workload involved in Convolutional Neural Networks (CNNs) is typically out of reach for low-power embedded devices. There are a large number of approximation techniques to address this problem. These methods have hyper-parameters that need to be optimized for each CNNs using design space exploration (DSE). The goal of this work is to demonstrate that the DSE phase time can easily explode for state of the art CNN. We thus propose the use of an optimized exploration process to drastically reduce the exploration time without sacrificing the quality of the output.
## Skill Description
This skill is generated from the arXiv paper: Fast Exploration of Weight Sharing Opportunities for CNN Compression (2102.01345).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2102.01345](http://arxiv.org/abs/2102.01345v1)
