Skip to Main Content
This paper presents an alternative to construct support vector machine (SVM) kernels from orthogonal polynomials. After describing some knowledge about orthogonal polynomials, we construct kernels from orthogonal polynomials according to Mercer's condition. The elegant and fascinating characteristics of the orthogonal polynomials promise the minimum data redundancy in feature space and make it possible to represent the data with less support vectors. Experimental results show that the SVMs with orthogonal polynomial kernels outperform that with traditional kernels in terms of generalization power and less support vectors.