Projection learning

作     者：Valiant, LG 

作者机构：Harvard Univ Div Engn & Appl Sci Cambridge MA 02138 USA 

出 版 物：《MACHINE LEARNING》 (机器学习)

年 卷 期：1999年第37卷第2期

页      面：115-130页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Science Foundation, NSF, (NSF-CCR-95-04436) Office of Naval Research, ONR, (ONR-N00014-96-1-0550) Army Research Office, ARO, (ARO-DAAL-03-92-G-0115) 

主　　题：computational learning attribute-efficient learning irrelevant attributes Winnow algorithm 

摘      要：A method of combining learning algorithms is described that preserves attribute-efficiency. It yields learning algorithms that require a number of examples that is polynomial in the number of relevant variables and logarithmic in the number of irrelevant ones. The algorithms are simple to implement and realizable on networks with a number of nodes linear in the total number of variables. They include generalizations of Littlestone s Winnow algorithm, and are, therefore, good candidates for experimentation on domains having very large numbers of attributes but where nonlinear hypotheses are sought.