.png){kind=icon}
返回
Pre-Computing Batch Normalisation Parameters for Edge Devices on a Binarized Neural Network
.png){kind=icon}
OA
AI
DOI：10.3390/s23125556.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Binarized Neural Network (BNN) is a quantized Convolutional Neural Network (CNN), reducing the precision of network parameters for a much smaller model size. In BNNs, the Batch Normalisation (BN) layer is essential. When running BN on edge devices, floating point instructions take up a significant number of cycles to perform. This work leverages the fixed nature of a model during inference, to reduce the full-precision memory footprint by half. This was achieved by pre-computing the BN parameters prior to quantization. The proposed BNN was validated through modeling the network on the MNIST dataset. Compared to the traditional method of computation, the proposed BNN reduced the memory utilization by 63% at 860-bytes without any significant impact on accuracy. By pre-computing portions of the BN layer, the number of cycles required to compute is reduced to two cycles on an edge device.
Keyword:
batch normalisation
binarized neural networks
convolutional neural networks
inference
edge devices
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:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
Estimation method of earthwork excavation using shield tunneling data -- a case study of Chengdu Metro盾构隧道数据在土方开挖估算方法中的应用——以成都地铁为例
OAAI
OAAI分享收藏Ionophore antibiotic X-206 is a potent and selective inhibitor of SARS-CoV-2 infectionin vitro.png)
OAAI
IF0
OAAI分享收藏Secret key generation in MIMO wireless systems using precoded channel measurements基于预编码信道测量的MIMO无线系统中的密钥生成
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Structural study of lanthanides(III) in aqueous nitrate and chloride solutions by EXAFS通过EXAFS对硝酸盐和氯化物水溶液中镧系元素 (III) 的结构研究
PREAI
分享收藏
查看更多内容