An evolutionary method for constructing complex SVM kernels

The aim of this paper is to construct and analyze multiple SVM kernels. The construction is based on a genetic algorithm which uses a new co-mutation operator called LR-Mijn, capable of operating on a set of adjacent bits in one single step.

[1]  Ernesto Tarantino,et al.  A Comparative Analysis of Evolutionary Algorithms for Function Optimisation , 1996 .

[2]  Mihai Oltean,et al.  Genetically designed multiple-kernels for improving the SVM performance , 2007, GECCO '07.

[3]  E. Tarantino,et al.  MijnMutation Operator for Aerofoil Design Optimisation , 1998 .

[4]  E. Tarantino,et al.  The effectiveness of co-mutation in evolutionary algorithms: the /spl Mscr//sub ijn/ operator , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[5]  Dana Simian,et al.  A model for a complex polynomial SVM kernel , 2008 .

[6]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[7]  G. Baudat,et al.  Kernel-based methods and function approximation , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[8]  Gunnar Rätsch,et al.  Large Scale Multiple Kernel Learning , 2006, J. Mach. Learn. Res..

[10]  Mihai Oltean,et al.  Improving SVM Performance Using a Linear Combination of Kernels , 2007, ICANNGA.

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[13]  J. Mesirov,et al.  Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. , 1999, Science.