Date of Graduation

Spring 2018

Degree

Master of Science in Mathematics

Department

Mathematics

Committee Chair

Songfeng Zheng

Keywords

Support Vector Machine; Multi-class Classification; Linear Model; Non-Linear Classifier; Kernel Function

Subject Categories

Computational Engineering | Robotics

Abstract

Support Vector Machine(SVM) is a widely-used tool for pattern classification problems. The main idea behind SVM is to separate two different groups with a hyperplane which makes the margin of these two groups maximized. It doesn't require any knowledge about the object we are focused on, since it can catch the features automatically. The idea of SVM can be easily generalized to nonlinear model by a mapping from the original space to a high-dimensional feature space, and they construct a max-margin linear classifier in the high dimensional feature space.

This thesis will investigate the basic idea of SVM and apply its application to multiclass case, that is, one vs. all and one vs. one strategies. As an application, we will apply the scheme to the problem of handwritten digital recognition. We show the difference of performance between linear and non linear technology, in terms of confusing matrix and running time.

Copyright

© Yu Wang

Open Access

Share

COinS