.png){kind=icon}
返回
Quantization-Aware Pruning Criterion for Industrial Applications
.png){kind=icon}
PRE
AI
DOI：10.1109/TIE.2021.3070517.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Y In this study, we propose a simple and effective quantization-aware neural network pruning method to prune and quantize deep neural networks and then run them on lightweight and cost-effective embedded industrial devices. The proposed pruning method provides a suitable pruning strategy for a given bit precision before performing the subsequent quantization. In particular, the dropout rate is set to be bounded below by the maximum number of quantization levels, which enables the regulation of the tradeoff between sparsity and performance loss. The Kullback-Leibler divergence term of the evidence lower bound is also weighted for adjusting the performance loss. From learned dropout rates, efficient bit allocation is provided to maintain randomness even through the quantization step. In supervised and reinforcement learning applications, the proposed quantization-aware pruning method was proven to be successful in obtaining sparse and lightweight neural networks while maintaining their performance even after quantization. In particular, a real inverted pendulum system was used to determine whether the proposed method works well for actual physical control systems.
Keyword:
Network compression
network pruning
sparse variational dropout
uniform scalar quantization
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.2
论文数:
1.8W
被引数:
9.8W
机构
暂无机构信息
引用论文
Informative presence and observation in routine health data: A review of methodology for clinical risk prediction常规健康数据中的信息存在和观察: 临床风险预测方法的回顾
OAAI
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏
查看更多内容