Textbook Information / Reading Materials
There is no required text. The content of the course is based mostly on the following publications, recommended as additional reading:
Learning with Kernels, B. Schölkopf, A. J. Smola, 2002
- Extensive presentation of support vector machines (SVMs) and other kernel methods in general, way beyond the scope of this course. You should buy this book after completing this course, when you feel like knowing more.
- Book is on library reserve (Q325.5 .S32 2002)
- Amazon: Learning with Kernels
Support Vector Machines for Pattern Classification, S. Abe, 2005
- Apart from two-class SVMs, a significant portion of this book is devoted to the problem of multi-class SVM classification. Possible improvements of other classification techniques (neural networks / fuzzy classifiers) by incorporating the ideas of SVMs are also discussed. This book focuses on practical applications rather than on the theoretical aspects of SVMs.
- Book is on library reserve (QA76.9.T48 A23 2005)
- Amazon: Support Vector Machines for Pattern Classification
Support Vector Machines and other kernel-based learning methods, N. Cristianini, J. Shawe-Taylor, 2000
- If you want to buy one book, buy this one. It is a self-contained coverage of binary support vector classification and regression compressed into less than 200 pages. Multi-classification or other kernel-based methods are not covered.
- Book's website: http://www.support-vector.net
Selected on-line tutorials
- Kernel Methods in Machine Learning, T. Hofmann, B. Schölkopf, A. Smola (2008)
- A Tutorial on v-Support Vector Machines, P. H. Chen, C. J. Lin, B. Schölkopf, 2005
- A Tutorial on Support Vector Machines for Pattern Recognition, Christopher J. C. Burges, 1998
SVM Gateways ( links to more tutorials / books / papers / lectures / software )
- http://www.kernel-machines.org (seems to be better maintained)
- http://www.support-vector-machines.org
Videolectures on SVMs
- More than 40 SVM-related videolectures with downloadable slides: here