A new method for multiclass support vector machines.

被引：10

作者：

Anguita, D ^{[1
]}

Ridella, S ^{[1
]}

Sterpi, D ^{[1
]}

机构：

[1] Univ Genoa, DIBE, Dept Biophys & Elect Engn, I-16145 Genoa, Italy

来源：

2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS | 2004年

关键词：

D O I：

10.1109/IJCNN.2004.1379940

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we present a new method for solving multiclass problems with a Support Vector Machine. Our method compares favorably with other proposals, appeared so far in the literature, both in terms of computational needs for the feedforward phase and of classification accuracy. The main result, however, is the mapping of the multiclass problem to a biclass one, which allows us to suggest a method for estimating the generalization error by using data-dependent error bounds.

引用

页码：407 / 412

页数：6

共 19 条

[1] Hyperparameter design criteria for support vector classifiers
Anguita, D
Ridella, S
Rivieccio, F
Zunino, R
[J]. NEUROCOMPUTING, 2003, 55 (1-2) : 109 - 134
[2] ANGUITA D, UNPUB INPUT CODING M
[3] [Anonymous], ADV NEURAL INFORM PR
[4] [Anonymous], ADV KERNEL METHODS
[5] BARTLETT PL, 2000, P 13 ANN C COMP LEAR, P286
[6] Blake C.L., 1998, UCI repository of machine learning databases
[7] CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
[8] On the learnability and design of output codes for multiclass problems
Crammer, K
Singer, Y
[J]. MACHINE LEARNING, 2002, 47 (2-3) : 201 - 233
[9] DESYATNIKOV D, 2003, P 16 ANN C COMP LEAR, P159
[10] Dietterich T. G., 1995, Journal of Artificial Intelligence Research, V2, P263

← 1 2 →