VC-dimension on manifolds: a first approach

被引：1

作者：

Ferri, Massimo ^{[1
,2
]}

Frosini, Patrizio ^{[1
,2
]}

机构：

[1] ARCES, I-40126 Bologna, Italy

[2] Dept Math, I-40126 Bologna, Italy

来源：

MATHEMATICAL METHODS IN THE APPLIED SCIENCES | 2008年 / 31卷 / 05期

关键词：

statistical learning; covering projection; Vapnik-Chervonenkis-dimension; Morse function;

D O I：

10.1002/mma.927

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

The Vapnik-Chervonenkis-dimension is an index of the capacity of a learning machine. It has been computed in several cases, but always in a Euclidean context. This paper extends the notion to classifiers acting in the more general environment of a manifold. General properties are proved, and some examples of simple classifiers on elementary manifolds are given. A large part of the research is directed toward a still open problem on product manifolds. Copyright (C) 2007 John Wiley & Sons, Ltd.

引用

页码：589 / 605

页数：17

共 13 条

[1]

[Anonymous], 2000, GRAPHS APPL INTRO AP

[2] Semi-supervised learning on Riemannian manifolds [J].

Belkin, M ;

Niyogi, P .

MACHINE LEARNING, 2004, 56 (1-3) :209-239

[3] A tutorial on Support Vector Machines for pattern recognition [J].

Burges, CJC .

DATA MINING AND KNOWLEDGE DISCOVERY, 1998, 2 (02) :121-167

[4]

Cristianini N., 2000, Intelligent Data Analysis: An Introduction

[5]

Cucker F, 2002, B AM MATH SOC, V39, P1

[6]

DREISEITL S, 2002, SUPPORT VECTOR MACHI

[7] Lower bound on VC-dimension by local shattering [J].

Erlich, Y ;

Chazan, D ;

Petrack, S ;

Levy, A .

NEURAL COMPUTATION, 1997, 9 (04) :771-776

[8]

Mardia K., 2000, Directional Statistics

[9]

Milnor J., 1963, MORSE THEORY

[10]

Sontag E. D., 1998, Neural Networks and Machine Learning. Proceedings, P69

← 1 2 →