Affiliation:
1. School of Mathematics and Statistics , Shandong University of Technology , Zibo , PR China
Abstract
Abstract
The efficiency of support vector machine in practice is closely related to the optimal selection of kernel functions and their hyper-parameters. A novel kernel, namely the arctangent kernel, is proposed in this paper. Compared with the Gaussian kernel, the new proposed kernel has a quick similarity descent in the neighborhood of the inspection sample and a moderate similarity descent toward the infinity of the inspection sample. The experimental results on two simulated data sets and some UCI data sets show that the new proposed kernel function has better effectiveness and robustness compared with the polynomial kernel, the Gaussian kernel, the exponential radial basis function, and the former proposed kernel with moderate decreasing.
Subject
Applied Mathematics,Engineering (miscellaneous),Modeling and Simulation,General Computer Science
Reference27 articles.
1. [1] V. N. Vapnik, 1. (1998), The Nature of Statistical Learning Theory, 2nd ed., Springer-Verlag, New York, USA, pp. 493–520.
2. [2] B. Schölkopf, A.J. Smola, K.-R.Müller, 2. (1999), Kernel principal component analysis,” in: M. Press (Ed.), Advances in kernel methods: support vector learning, pp.327–352.
3. [3] J. Liu, X Liu, J Xiong, et al., 3. (2020), Optimal Neighborhood Multiple Kernel Clustering with Adaptive Local Kernels. IEEE Transactions on Knowledge and Data Engineering, pp. 99.
4. [4] S. Mika, et al.,4. (1999), Fisher discriminant analysis with kernels, Neural Networks for Signal Processing IX”, in: Proceedings of the 1999 IEEE Signal Processing Society Workshop, pp.41–48.
5. [5] D.R. Hardoon, S. Szedmak, J. Shawe-Taylor, 5. (2004), Canonical correlation analysis: an overview with application to learning method, Neural Computation, 16(12), pp.2639–2664.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献