Parallel learning: a perspective and a framework
Li li; Yilun Lin; Nanning Zheng; Fei-Yue Wang
2017
发表期刊IEEE/CAA Journal of Automatica Sinica
卷号4期号:3页码:389-395
摘要
; The development of machine learning in complex system is hindered by two problems nowadays.The first problem is the inefficiency of exploration in state and action space, which leads to the data-hungry of some state-of-art data-driven algorithm.The second problem is the lack of a general theory which can be used to analyze and implement a complex learning system.In this paper,we proposed a general methods that can address both two issues.We combine the concepts of descriptive learning,predictive learning,and prescriptive learning into a uniform framework,so as to build a parallel system allowing learning system improved by self-boosting.Formulating a new perspective of data,knowledge and action,we provide a new methodology called parallel learning to design machine learning system for real-world problems.
关键词Descriptive Learning Machine Learning Parallel Learning Parallel Systems Perspective Learning Perspective-learning
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/20162
专题复杂系统管理与控制国家重点实验室_先进控制与自动化
推荐引用方式
GB/T 7714
Li li,Yilun Lin,Nanning Zheng,et al. Parallel learning: a perspective and a framework[J]. IEEE/CAA Journal of Automatica Sinica,2017,4(3):389-395.
APA Li li,Yilun Lin,Nanning Zheng,&Fei-Yue Wang.(2017).Parallel learning: a perspective and a framework.IEEE/CAA Journal of Automatica Sinica,4(3),389-395.
MLA Li li,et al."Parallel learning: a perspective and a framework".IEEE/CAA Journal of Automatica Sinica 4.3(2017):389-395.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Parallel learning a (1334KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li li]的文章
[Yilun Lin]的文章
[Nanning Zheng]的文章
百度学术
百度学术中相似的文章
[Li li]的文章
[Yilun Lin]的文章
[Nanning Zheng]的文章
必应学术
必应学术中相似的文章
[Li li]的文章
[Yilun Lin]的文章
[Nanning Zheng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Parallel learning a perspective and a framework.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。