A RESULT OF VAPNIK WITH APPLICATIONS

被引：36

作者：

ANTHONY, M ^{[1
]}

SHAWETAYLOR, J ^{[1
]}

机构：

[1] UNIV LONDON ROYAL HOLLOWAY & BEDFORD NEW COLL,DEPT COMP SCI,EGHAM TW20 0EX,SURREY,ENGLAND

来源：

DISCRETE APPLIED MATHEMATICS | 1993年 / 47卷 / 03期

关键词：

D O I：

10.1016/0166-218X(93)90126-9

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

A new proof of a result due to Vapnik is given. Its implications for the theory of PAC learnability are discussed, with particular reference to the learnability of functions taking values in a countable set. An application to the theory of artificial neural networks is then given.

引用

页码：207 / 217

页数：11

共 16 条

[1]

ANTHONY M, 1990, COLT 90, P246

[2] What Size Net Gives Valid Generalization? [J].

Baum, Eric B. ;

Haussler, David .

NEURAL COMPUTATION, 1989, 1 (01) :151-160

[3]

BIGGS N, IN PRESS DISCRETE MA

[4] LEARNABILITY AND THE VAPNIK-CHERVONENKIS DIMENSION [J].

BLUMER, A ;

EHRENFEUCHT, A ;

HAUSSLER, D ;

WARMUTH, MK .

JOURNAL OF THE ACM, 1989, 36 (04) :929-965

[5] DECISION THEORETIC GENERALIZATIONS OF THE PAC MODEL FOR NEURAL NET AND OTHER LEARNING APPLICATIONS [J].

HAUSSLER, D .

INFORMATION AND COMPUTATION, 1992, 100 (01) :78-150

[6] QUANTIFYING INDUCTIVE BIAS - AI LEARNING ALGORITHMS AND VALIANTS LEARNING FRAMEWORK [J].

HAUSSLER, D .

ARTIFICIAL INTELLIGENCE, 1988, 36 (02) :177-221

[7]

HAUSSLER D, 1989, UCSCCRL8930 U CAL CO

[8]

McClelland J. L., 1986, PARALLEL DISTRIBUTED, V1

[9]

Natarajan B. K., 1989, Machine Learning, V4, P67, DOI 10.1023/A:1022605311895

[10]

Pollard D., 1984, CONVERGENCE STOCHAST

← 1 2 →