發(fā)信人: GzLi (笑梨), 信區(qū): DataMining
標  題: Re: [轉載] 請教：regression和classification有何異
發(fā)信站: 南京大學小百合站 (Sun May 25 22:20:30 2003)

【 以下文字轉載自 AI 討論區(qū) 】
【 原文由 daniel 所發(fā)表 】


【 在 cczhu (congcongzhu) 的大作中提到: 】
: Dr. Z.-H.Zhou 的一片paper提到“regression and classification have distinct cha
: racteristics”。但regression也可以通過classification得到近似解，而classificati
: on更是可以通過regression之后再進行離散化處理得到。這樣看來，兩類問題在原理上應
: 該是類似的。那Dr.Zhou指的不同在什么地方呢？
: 
: 更請daniel不吝指教，謝謝！


I guess he meant the nature of these two things are different. for example,
classification usually employs zero-one loss while regression does not.
since many good properties are not held by zero-one loss, the mathematical
tools for anlyzing classification seems fewer than that for regression.
it is hard to useclassification to approximate regression, even you come with
some king of smoothing technique, the result won't be encouraging. it is
possible to use regression technique to tackle classifiction problems, but
some kind of thresholding is necessary.

--
寵辱不驚  閑看庭前花開花落
去留無意  漫隨天外云卷云舒

※ 來源:．南京大學小百合站 bbs.nju.edu.cn．[FROM: dialup61-118.nju.edu]
--
※ 轉載:．南京大學小百合站 bbs.nju.edu.cn．[FROM: 202.120.8.48]