arrow
返回

Performance and efficiency: Recent advances in supervised learning

delete1999-01-01
delete37
PRE
AI
S
Sheng Ma
C
Chuanyi Ji
DOI:10.1109/5.784228delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
This paper reviews recent advances in supervised learning with a focus on two most important issues: performance and efficiency. Performance addresses the generalization capability of a learning machine on randomly chosen samples that are not included in a training set. Efficiency deals with the complexity of a learning machine in both space and time. As these two issues are general to various learning machines nod learning approaches, we focus on a special type of adaptive learning systems with a neural architecture. We discuss four types of learning approaches. training all individual model; combinations of several well-trained models; combinations of many weak models; and evolutionary computation of models. We explore advantages and weaknesses of each approach and their inter relations, and we pose open questions for possible future research.
Keyword:
evolutionary computation
hybrid models
neural networks
supervised learning
AI总结

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

Proceedings of the IEEE 封面图
Proceedings of the IEEE
IF:
25.9
论文数:
9.9K
被引数:
4.5W

机构

暂无机构信息
引用论文

引用论文

err分享
err收藏
Diseases and Molecular Diagnostics: A Step Closer to Precision Medicine
err2017-08-22
err0
errOAAI
errShailendra Dwivedi; Purvi Purohit; Radhieka Misra; Puneet Pareek; Apul Goel; Sanjay Khattri; Kamlesh Kumar Pant; Sanjeev Misra; Praveen Sharma
err分享
err收藏
A THEORY OF THE LEARNABLE
err1984-11-05
err2.4K
errOAAI
errVALIANT, LG
err分享
err收藏
A heterodimeric cytochrome c complex with a very low redox potential from an anaerobic ammonium-oxidizing enrichment culture
err2010-09-30
err0
errOAAI
errSaki Ukita; Takao Fujii; Daisuke Hira; Takashi Nishiyama; Tatsushi Kawase; Catharina T. Migita; Kenji Furukawa
err分享
err收藏
学者 查看更多内容