Training Binary Neural Networks Without Floating Point Precision
ASecurity
**arXiv ID:** 2310.19815 **Authors:** Federico Fontana **Published:** 2023-10-19T13:48:21Z **Abstract:** The main goal of this work is to improve the efficiency of training binary neural networks, which are low latency and low energy networks. The main contribution of this work is the proposal of two solutions comprised of topology changes and strategy training that allow the network to achieve near the state-of-the-art performance and efficient training. The time required for training and th...
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 Training Binary Neural Networks Without Floating Point Precision?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-training-binary-neural-networks-without-floating-p)
# Training binary neural networks without floating point precision
**arXiv ID:** 2310.19815
**Authors:** Federico Fontana
**Published:** 2023-10-19T13:48:21Z
**Abstract:**
The main goal of this work is to improve the efficiency of training binary neural networks, which are low latency and low energy networks. The main contribution of this work is the proposal of two solutions comprised of topology changes and strategy training that allow the network to achieve near the state-of-the-art performance and efficient training. The time required for training and the memory required in the process are two factors that contribute to efficient training.
## Skill Description
This skill is generated from the arXiv paper: Training binary neural networks without floating point precision (2310.19815).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2310.19815](http://arxiv.org/abs/2310.19815v1)
