Evolutionary Optimisation of Kernel Functions for Svms

The kernel-based classifiers use one of the classical kernels, but the real-world applications have emphasized the need to consider a new kernel function in order to boost the classification accuracy by a better adaptation of the kernel function to the characteristics of the data. Our purpose is to automatically design a complex kernel by evolutionary means. In order to achieve this purpose we develop a hybrid model that combines a Genetic Programming (GP) algorithm and a kernel-based Support Vector Machine (SVM) classifier. Each GP chromosome is a tree encoding the mathematical expression of the kernel function. The evolved kernel is compared to several human-designed kernels and to a previous genetic kernel on several datasets. Numerical experiments show that the SVM embedding our evolved kernel performs statistically better than standard kernels, but also than previous genetic kernel for the considered classification problems.