Analysis of convergence performance of neural networks ranking algorithm

被引：9

作者：

Zhang, Yongquan ^{[1
]}

Cao, Feilong ^{[1
]}

机构：

[1] China Jiliang Univ, Dept Informat & Math Sci, Hangzhou 310018, Zhejiang, Peoples R China

来源：

NEURAL NETWORKS | 2012年 / 34卷

基金：

中国国家自然科学基金;

关键词：

Ranking algorithm; Neural networks; Covering number; Convergence rate; APPROXIMATION CAPABILITY; UNIVERSAL APPROXIMATION; LEARNING-THEORY; BOUNDS; OPERATORS; REGRESSION; NUMBERS; ORDER;

D O I：

10.1016/j.neunet.2012.06.012

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The ranking problem is to learn a real-valued function which gives rise to a ranking over an instance space, which has gained much attention in machine learning in recent years. This article gives analysis of the convergence performance of neural networks ranking algorithm by means of the given samples and approximation property of neural networks. The upper bounds of convergence rate provided by our results can be considerably tight and independent of the dimension of input space when the target function satisfies some smooth condition. The obtained results imply that neural networks are able to adapt to ranking function in the instance space. Hence the obtained results are able to circumvent the curse of dimensionality on some smooth condition. Crown Copyright (C) 2012 Published by Elsevier Ltd. All rights reserved.

引用

页码：65 / 71

页数：7

共 35 条

[1]

Agarwal S, 2009, J MACH LEARN RES, V10, P441

[2]

[Anonymous], P 18 ANN C LEARN THE

[3]

[Anonymous], 2003, Journal of machine learning research

[4] UNIVERSAL APPROXIMATION BOUNDS FOR SUPERPOSITIONS OF A SIGMOIDAL FUNCTION [J].

BARRON, AR .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1993, 39 (03) :930-945

[5]

Burges C.J.C., 2005, ICML

[6]

Cao F. L., 2009, SCI CHINA SER F, V52, P1283

[7] Interpolation and rates of convergence for a class of neural networks [J].

Cao, Feilong ;

Zhang, Yongquan ;

He, Ze-Rong .

APPLIED MATHEMATICAL MODELLING, 2009, 33 (03) :1441-1456

[8]

CHEN TP, 1995, IEEE T NEURAL NETWOR, V6, P25

[9] UNIVERSAL APPROXIMATION TO NONLINEAR OPERATORS BY NEURAL NETWORKS WITH ARBITRARY ACTIVATION FUNCTIONS AND ITS APPLICATION TO DYNAMICAL-SYSTEMS [J].

CHEN, TP ;

CHEN, H .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (04) :911-917

[10] APPROXIMATION CAPABILITY TO FUNCTIONS OF SEVERAL VARIABLES, NONLINEAR FUNCTIONALS, AND OPERATORS BY RADIAL BASIS FUNCTION NEURAL NETWORKS [J].

CHEN, TP ;

CHEN, H .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (04) :904-910

← 1 2 3 4 →