微型设备的自动神经搜索和设备上学习的定量综述

Danilo Pietro Pau, Prem Kumar Ambrose, Fabrizio Maria Aymone
{"title":"微型设备的自动神经搜索和设备上学习的定量综述","authors":"Danilo Pietro Pau, Prem Kumar Ambrose, Fabrizio Maria Aymone","doi":"10.3390/chips2020008","DOIUrl":null,"url":null,"abstract":"This paper presents a state-of-the-art review of different approaches for Neural Architecture Search targeting resource-constrained devices such as microcontrollers, as well as the implementations of on-device learning techniques for them. Approaches such as MCUNet have been able to drive the design of tiny neural architectures with low memory and computational requirements which can be deployed effectively on microcontrollers. Regarding on-device learning, there are various solutions that have addressed concept drift and have coped with the accuracy drop in real-time data depending on the task targeted, and these rely on a variety of learning methods. For computer vision, MCUNetV3 uses backpropagation and represents a state-of-the-art solution. The Restricted Coulomb Energy Neural Network is a promising method for learning with an extremely low memory footprint and computational complexity, which should be considered for future investigations.","PeriodicalId":6666,"journal":{"name":"2015 IEEE Hot Chips 27 Symposium (HCS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Quantitative Review of Automated Neural Search and On-Device Learning for Tiny Devices\",\"authors\":\"Danilo Pietro Pau, Prem Kumar Ambrose, Fabrizio Maria Aymone\",\"doi\":\"10.3390/chips2020008\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a state-of-the-art review of different approaches for Neural Architecture Search targeting resource-constrained devices such as microcontrollers, as well as the implementations of on-device learning techniques for them. Approaches such as MCUNet have been able to drive the design of tiny neural architectures with low memory and computational requirements which can be deployed effectively on microcontrollers. Regarding on-device learning, there are various solutions that have addressed concept drift and have coped with the accuracy drop in real-time data depending on the task targeted, and these rely on a variety of learning methods. For computer vision, MCUNetV3 uses backpropagation and represents a state-of-the-art solution. The Restricted Coulomb Energy Neural Network is a promising method for learning with an extremely low memory footprint and computational complexity, which should be considered for future investigations.\",\"PeriodicalId\":6666,\"journal\":{\"name\":\"2015 IEEE Hot Chips 27 Symposium (HCS)\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 IEEE Hot Chips 27 Symposium (HCS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/chips2020008\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE Hot Chips 27 Symposium (HCS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/chips2020008","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本文介绍了针对资源受限设备(如微控制器)的神经架构搜索的不同方法的最新综述,以及设备上学习技术的实现。像MCUNet这样的方法已经能够驱动具有低内存和计算需求的微型神经架构的设计,这些结构可以有效地部署在微控制器上。关于设备上学习,有各种解决方案可以解决概念漂移问题,并根据目标任务应对实时数据的准确性下降,这些解决方案依赖于各种学习方法。对于计算机视觉,MCUNetV3使用反向传播,代表了最先进的解决方案。限制库仑能量神经网络是一种很有前途的学习方法,具有极低的内存占用和计算复杂度,应该在未来的研究中加以考虑。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Quantitative Review of Automated Neural Search and On-Device Learning for Tiny Devices
This paper presents a state-of-the-art review of different approaches for Neural Architecture Search targeting resource-constrained devices such as microcontrollers, as well as the implementations of on-device learning techniques for them. Approaches such as MCUNet have been able to drive the design of tiny neural architectures with low memory and computational requirements which can be deployed effectively on microcontrollers. Regarding on-device learning, there are various solutions that have addressed concept drift and have coped with the accuracy drop in real-time data depending on the task targeted, and these rely on a variety of learning methods. For computer vision, MCUNetV3 uses backpropagation and represents a state-of-the-art solution. The Restricted Coulomb Energy Neural Network is a promising method for learning with an extremely low memory footprint and computational complexity, which should be considered for future investigations.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Winner-Take-All and Loser-Take-All Circuits: Architectures, Applications and Analytical Comparison A Survey of Automotive Radar and Lidar Signal Processing and Architectures Design and Performance Analysis of Hardware Realization of 3GPP Physical Layer for 5G Cell Search Silicon Carbide: Physics, Manufacturing, and Its Role in Large-Scale Vehicle Electrification Synergistic Verification of Hardware Peripherals through Virtual Prototype Aided Cross-Level Methodology Leveraging Coverage-Guided Fuzzing and Co-Simulation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1