Active Exploration in Building Hierarchical Neural Networks for Robotics

Q. Meng, M.H. Lee
{"title":"Active Exploration in Building Hierarchical Neural Networks for Robotics","authors":"Q. Meng, M.H. Lee","doi":"10.1109/IMTC.2006.328464","DOIUrl":null,"url":null,"abstract":"During early robot learning, several mappings need to be set up for sensorimotor coordinations and transformation of sensory information from one modality to another. Usually these mappings are nonlinear and traditional passive learning approaches can not deal with these problems well. In this paper, a hierarchical clustering technique is introduced to group large mapping error locations and these error clusters drive the system to actively explore details of these clusters. Higher level local growing radial basis function subnetworks are used to approximate the mapping residual errors from previous mapping levels. Plastic radial basis function networks construct the substrate of the learning system and a simplified node-decoupled extended Kalman filter algorithm is presented to train these radial basis function networks. Experimental results are given to compare the performance between active learning and passive learning","PeriodicalId":142185,"journal":{"name":"2006 IEEE Instrumentation and Measurement Technology Conference Proceedings","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2006 IEEE Instrumentation and Measurement Technology Conference Proceedings","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IMTC.2006.328464","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

During early robot learning, several mappings need to be set up for sensorimotor coordinations and transformation of sensory information from one modality to another. Usually these mappings are nonlinear and traditional passive learning approaches can not deal with these problems well. In this paper, a hierarchical clustering technique is introduced to group large mapping error locations and these error clusters drive the system to actively explore details of these clusters. Higher level local growing radial basis function subnetworks are used to approximate the mapping residual errors from previous mapping levels. Plastic radial basis function networks construct the substrate of the learning system and a simplified node-decoupled extended Kalman filter algorithm is presented to train these radial basis function networks. Experimental results are given to compare the performance between active learning and passive learning
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
构建机器人层次神经网络的积极探索
在机器人早期学习过程中,需要建立一些映射来进行感觉运动协调和感觉信息从一种模态到另一种模态的转换。通常这些映射是非线性的,传统的被动学习方法不能很好地处理这些问题。本文引入分层聚类技术对大的地图错误位置进行分组,这些错误簇驱动系统主动探索这些簇的细节。采用更高层次的局部增长径向基函数子网来逼近前一层次的映射残差。塑性径向基函数网络构成了学习系统的基础,并提出了一种简化的节点解耦扩展卡尔曼滤波算法来训练这些径向基函数网络。实验结果比较了主动学习和被动学习的性能
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Understanding the Nonlinearity of a Mixer Using Multisine Excitations A Distance Compensated Telemetric Humidity Sensor Based on the Parasitic Capacitance Variation Fine Tuning Design of Control Board Parameters for Sensing Applications A Power Measuring Technique for Built-in Test Purposes A Clamping Circuit Architecture Implementing Charges Injection Reduction Techniques
wanfang
×
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学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
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