Multi-scale Cauchy Kernel Function and Its Application in Multi-class SVM

The application of kernel function made support vector machine one of the research focuses in machine learning field. However, single kernel function is difficult to process complex data efficiently. Multiple kernel method is a common solution for this problem in recent years. The commonly used multiple kernel function is a weighted combination of different kernel function. It lacks the pertinence to a particular sample. A new multi-scale Cauchy kernel function is proposed in this paper. And an integrated classification method is proposed in order to improve the effectiveness of multi-scale kernel function. Experimental results show that the multi-scale Cauchy kernel function has good performance on complex problem.