A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory
The nature of statistical learning theory
Machine Learning
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Lagrangian support vector machines
The Journal of Machine Learning Research
Input space versus feature space in kernel-based methods
IEEE Transactions on Neural Networks
Successive overrelaxation for support vector machines
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
Support Vector Machines have been widely used in pattern recognition, regression estimation, and operator inversion. Optimization algorithm is the bottleneck of Support Vector Machines, determining its performance, affecting its practical applications in various fields widely. Ordinary algorithm cannot predict which vectors the Support Vector Machines will be sensitive to. This paper introduces a method that selects possible vectors from sample vectors. It is based on the conception of convex set. On linear separable case this method can exactly find promising vectors and reserve them in the training set. On linear inseparable cases this method finds the vectors that will have effect on the final hyper plane. On both cases it can simplify the training process by greatly reducing the number of training vectors just as shown in the examples.