Learning with Support Vector Machines

Preface......Page 10
Acknowledgments......Page 12
Introduction......Page 14
Support Vector Machines for binary classification......Page 15
Multi-class classification......Page 21
Learning with noise: soft margins......Page 22
Algorithmic implementation of Support Vector Machines......Page 27
Case Study 1: training a Support Vector Machine......Page 30
Case Study 2: predicting disease progression......Page 31
Case Study 3: drug discovery through active learning......Page 34
Other kernel-based learning machines......Page 40
Introducing a confidence measure......Page 42
One class classification......Page 43
Regression: learning with real-valued labels......Page 46
Structured output learning......Page 53
Properties of kernels......Page 58
Simple kernels......Page 60
Kernels for strings and sequences......Page 63
Kernels for graphs......Page 67
Multiple kernel learning......Page 69
Learning kernel combinations via a maximum margin approach......Page 70
Algorithmic approaches to multiple kernel learning......Page 72
Case Study 4: protein fold prediction......Page 75
Introduction to optimization theory......Page 78
Duality......Page 80
Constrained optimization......Page 82
Bibliography......Page 88
Authors' Biography......Page 96