An overview of statistical learning theory

被引:4177
作者
Vapnik, VN [1 ]
机构
[1] AT&T Bell Labs, Res, Red Bank, NJ 07701 USA
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1999年 / 10卷 / 05期
关键词
D O I
10.1109/72.788640
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Statistical learning theory was introduced in the late 1960's, Until the 1990's it was a purely theoretical analysis of the problem of function estimation from a given collection of data. In the middle of the 1990's new types of learning algorithms (called support vector machines) based on the developed theory mere proposed, This made statistical learning theory not only a tool for the theoretical analysis hut also a tool for creating practical algorithms for estimating multidimensional functions. This article presents a very general overview of statistical learning theory including both theoretical and algorithmic aspects of the theory. The goal of this overview is to demonstrate how the abstract learning theory established conditions for generalization which are more general than those discussed in classical statistical paradigms and how the understanding of these conditions inspired new algorithmic approaches to function estimation problems. ih more detailed overview of the theory (without proofs) can be found in Vapnik (1995), In Vapnik (1998) one can find detailed description of the theory (including proofs).
引用
收藏
页码:988 / 999
页数:12
相关论文
共 30 条
[1]   Scale-sensitive dimensions, uniform convergence, and learnability [J].
Alon, N ;
BenDavid, S ;
CesaBianchi, N ;
Haussler, D .
JOURNAL OF THE ACM, 1997, 44 (04) :615-631
[2]  
[Anonymous], 1982, ESTIMATION DEPENDENC
[3]  
[Anonymous], P 13 INT C MACH LEAR
[4]  
[Anonymous], UNIFORM CONVERGENCE
[5]   Fat-shattering and the learnability of real-valued functions [J].
Bartlett, PL ;
Long, PM ;
Williamson, RC .
JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1996, 52 (03) :434-452
[6]  
BARTLETT PL, 1999, ADV KERNEL METHODS S
[7]   LEARNABILITY AND THE VAPNIK-CHERVONENKIS DIMENSION [J].
BLUMER, A ;
EHRENFEUCHT, A ;
HAUSSLER, D ;
WARMUTH, MK .
JOURNAL OF THE ACM, 1989, 36 (04) :929-965
[8]  
Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
[9]  
CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
[10]  
DEVROYE L, 1996, PROBABILITY THEORY P