Motor initiated expectation through top-down connections as abstract context in a physical world

M. Luciw, J. Weng, Shuqing Zeng
{"title":"Motor initiated expectation through top-down connections as abstract context in a physical world","authors":"M. Luciw, J. Weng, Shuqing Zeng","doi":"10.1109/DEVLRN.2008.4640815","DOIUrl":null,"url":null,"abstract":"Recently, it has been shown that top-down connections improve recognition in supervised learning. In the work presented here, we show how top-down connections represent temporal context as expectation and how such expectation assists perception in a continuously changing physical world, with which an agent interacts during its developmental learning. In experiments in object recognition and vehicle recognition using two types of networks (which derive either global or local features), it is shown how expectation greatly improves performance, to nearly 100% after the transition periods. We also analyze why expectation will improve performance in such real world contexts.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"19","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 7th IEEE International Conference on Development and Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DEVLRN.2008.4640815","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 19

Abstract

Recently, it has been shown that top-down connections improve recognition in supervised learning. In the work presented here, we show how top-down connections represent temporal context as expectation and how such expectation assists perception in a continuously changing physical world, with which an agent interacts during its developmental learning. In experiments in object recognition and vehicle recognition using two types of networks (which derive either global or local features), it is shown how expectation greatly improves performance, to nearly 100% after the transition periods. We also analyze why expectation will improve performance in such real world contexts.
在物理世界中,运动通过自上而下的连接作为抽象情境而启动期望
最近,研究表明,自上而下的联系可以提高监督学习中的认知能力。在这里的工作中,我们展示了自上而下的连接如何将时间上下文表示为期望,以及这种期望如何在不断变化的物理世界中帮助感知,agent在其发展学习过程中与物理世界相互作用。在物体识别和车辆识别的实验中,使用两种类型的网络(分别获得全局或局部特征),表明期望如何极大地提高了性能,在过渡期后几乎达到100%。我们还分析了为什么期望会在这样的现实环境中提高性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信