An Equivalent Form of S-L Projection Learning

作     者：LIU Benyong~1 OGAWA Hidemitsu~2(1.School of Electronic Engineering,UESTC Chengdu 610054 China 2.Dept.of Computer Science,Graduate School of Information Science and Technology,Tokyo Institute of Technology Tokyo 52-8552 Japan) 

作者机构：School of Electronic Engineering UESTC Chengdu 610054 China Dept. of Computer Science Graduate School of Information Science and Technology Tokyo InstituteofTechnology Tokyo 52-8552 Japan 

出 版 物：《Journal of Electronic Science and Technology of China》 (中国电子科技（英文版）)

年 卷 期：2003年第1卷第1期

页      码：6-11页

摘      要：Learning a mapping between an input space and an *** from training data canbe viewed as a problem of function approximation,which means that different criteria result in learningapproaches of different *** them,projection criterion proposed by one of the authors aimsdirectly at optimal *** projection idea leads to three specific learning approaches,projection learning,partial projection learning,and averaged projection learning,and a framework of afamily of projection learning called S-L projection learning is established to discuss infinite kinds oflearning.S-L projection learning has a different form from the three methods,and it is not easy to analyzetheir *** paper focuses on an equivalent form of S-L projection learning,which shows thatit is a transformed version of partial projection learning.

主 题 词：supervised learning generalization projection learning S-L projection learning 

学科分类：1305[艺术学-设计学类] 13[艺术学] 081104[081104] 08[工学] 0804[工学-材料学] 081101[081101] 0811[工学-水利类] 

馆 藏 号：203238833...