Paper Info
Title
KMOD - a new support vector machine kernel with moderate decreasing for pattern recognition. Application to digit image recognition
Abstract
A new direction in machine learning area has emerged from Vapnik's theory in support vectors machine (SVM) and its applications on pattern recognition. In this paper we propose a new SVM kernel family, called KMOD (kernel with moderate decreasing) with distinctive properties that allow better discrimination in the feature space. The experiments that we carry out show its effectiveness on synthetic and large-scale data. We found KMOD performs better than RBF and exponential RBF kernels on the two-spiral problem. In addition, a digit recognition task was processed using the proposed kernel. The results show, at least, comparable performances to state of the art kernels
Year
DOI
Venue
2001
10.1109/ICDAR.2001.953976
ICDAR-1
Keywords
Field
DocType
valmik theory,learning automata,new support,better discrimination,pattern recognition,proposed kernel,kmod,learning systems,digit image recognition,vector machine kernel,comparable performance,art kernel,digit recognition task,moderate decreasing,new direction,exponential rbf kernel,machine learning,support vectors machine,new svm kernel family,spirals,image recognition,digital image,feature space,risk management,support vector machine,upper bound,kernel,support vector machines
Graph kernel,Radial basis function kernel,Computer science,Tree kernel,Feature (machine learning),Polynomial kernel,Artificial intelligence,Computer vision,Least squares support vector machine,Pattern recognition,Support vector machine,Speech recognition,Kernel method
Conference
ISSN
ISBN
Citations 
1520-5363
0-7695-1263-1
21
PageRank 
References 
Authors
1.26
5
4
Name
Order
Citations
PageRank
Ayat, N.E.1855.14
Mohamed Cheriet22047238.58
Remaki, L.3453.98
Suen, C.Y.4627107.95