2005
DOI: 10.1007/s10462-005-9009-3
|View full text |Cite
|
Sign up to set email alerts
|

The Genetic Kernel Support Vector Machine: Description and Evaluation

Abstract: The Support Vector Machine (SVM) has emerged in recent years as a popular approach to the classification of data. One problem that faces the user of an SVM is how to choose a kernel and the specific parameters for that kernel. Applications of an SVM therefore require a search for the optimum settings for a particular problem. This paper proposes a classification technique, which we call the Genetic Kernel SVM (GK SVM), that uses Genetic Programming to evolve a kernel for a SVM classifier. Results of initial ex… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
69
0

Year Published

2006
2006
2011
2011

Publication Types

Select...
5
3
2

Relationship

1
9

Authors

Journals

citations
Cited by 142 publications
(69 citation statements)
references
References 16 publications
0
69
0
Order By: Relevance
“…In [21], GP is used to evolve kernels for Support Vector Machines. Both scalar and vector operations are used in the function set.…”
Section: Related Workmentioning
confidence: 99%
“…In [21], GP is used to evolve kernels for Support Vector Machines. Both scalar and vector operations are used in the function set.…”
Section: Related Workmentioning
confidence: 99%
“…Additionally, there are basically three main areas of weighting application in supervised machine learning: support vector machines optimization, artificial neural networks (training and topology) and feature weighting. Thus, SVM kernel [8] or artificial neural networks [9] parameters can be optimized by means of genetic algorithms or genetic programming with good results. In this context, evolutionary algorithms are usually employed to find a set of weights for the feature space, allowing greater accuracy in the classification process [10].…”
Section: Introductionmentioning
confidence: 99%
“…In 2005, Friedrichs and Igel [16] initiated a so-called covariance matrix adaptation evolution strategy (CMA-ES) to extend the RBF kernel with scaling and rotation in order to realize invariance against linear transformation in the space of SVMs parameters. In [17], Howley and Madden proposed a new approach to use a so-called genetic kernel, which is represented by a tree each leaf node of which expresses a feature vector (i.e., any data point or instance). Although this work sounded the first attempt to apply genetic programming to select an optimal kernel in SVM, it is not formulated well and the experiments were limited.…”
Section: Introductionmentioning
confidence: 99%