Applications of Support Vector Machines in Chemistry

Support vector machines represent an extension to nonlinear models of the generalized portrait algorithm developed by Vapnik and Lerner, and are a group of supervised learning methods that can be applied to classification or regression.

Abstract

This chapter contains sections titled: Introduction A Nonmathematical Introduction to SVM Pattern Classification The Vapnik–Chervonenkis Dimension Pattern Classification with Linear Support Vector Machines Nonlinear Support Vector Machines SVM Regression Optimizing the SVM Model Practical Aspects of SVM Classification Practical Aspects of SVM Regression Review of SVM Applications in Chemistry SVM Resources on the Web SVM Software Conclusions References