Skip to content
Back to skills

Magic For The Age Of Quantized Dnns

ASecurity

**arXiv ID:** 2403.14999 **Authors:** Yoshihide Sawada, Ryuji Saiin, Kazuma Suetake **Published:** 2024-03-22T07:21:09Z **Abstract:** Recently, the number of parameters in DNNs has explosively increased, as exemplified by LLMs (Large Language Models), making inference on small-scale computers more difficult. Model compression technology is, therefore, essential for integration into products. In this paper, we propose a method of quantization-aware training. We introduce a novel normalization ...

  • 3 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 11, 2026
tools

Works with

  • cli

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill magic-for-the-age-of-quantized-dnns --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Magic For The Age Of Quantized Dnns?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Magic For The Age Of Quantized Dnns
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-magic-for-the-age-of-quantized-dnns/badge)](https://www.skillsdirectory.com/skills/hiyenwong-magic-for-the-age-of-quantized-dnns)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Magic for the Age of Quantized DNNs

**arXiv ID:** 2403.14999
**Authors:** Yoshihide Sawada, Ryuji Saiin, Kazuma Suetake
**Published:** 2024-03-22T07:21:09Z
**Abstract:**
Recently, the number of parameters in DNNs has explosively increased, as exemplified by LLMs (Large Language Models), making inference on small-scale computers more difficult. Model compression technology is, therefore, essential for integration into products. In this paper, we propose a method of quantization-aware training. We introduce a novel normalization (Layer-Batch Normalization) that is independent of the mini-batch size and does not require any additional computation cost during inference. Then, we quantize the weights by the scaled round-clip function with the weight standardization. We also quantize activation functions using the same function and apply surrogate gradients to train the model with both quantized weights and the quantized activation functions. We call this method Magic for the age of Quantised DNNs (MaQD). Experimental results show that our quantization method can be achieved with minimal accuracy degradation.

## Skill Description

This skill is generated from the arXiv paper: Magic for the Age of Quantized DNNs (2403.14999).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2403.14999](http://arxiv.org/abs/2403.14999v1)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.