Advanced Lectures on Machine Learning

1. Front Matter

   Pages I-X

   PDF

2. A Few Notes on Statistical Learning Theory

   • Shahar Mendelson

   Pages 1-40

3. A Short Introduction to Learning with Kernels

   • Bernhard Schölkopf, Alexander J. Smola

   Pages 41-64

4. Bayesian Kernel Methods

   • Alexander J. Smola, Bernhard Schölkopf

   Pages 65-117

5. An Introduction to Boosting and Leveraging

   • Ron Meir, Gunnar Rätsch

   Pages 118-183

6. An Introduction to Reinforcement Learning Theory: Value Function Methods

   • Peter L. Bartlett

   Pages 184-202

7. Learning Comprehensible Theories from Structured Data

   • J.W. Lloyd

   Pages 203-225

8. Algorithms for Association Rules

   • Markus Hegland

   Pages 226-234

9. Online Learning of Linear Classifiers

   • Jyrki Kivinen

   Pages 235-257

10. Back Matter

    Pages 259-259

    PDF

Machine Learning has become a key enabling technology for many engineering applications and theoretical problems alike. To further discussions and to dis- minate new results, a Summer School was held on February 11–22, 2002 at the Australian National University. The current book contains a collection of the main talks held during those two weeks in February, presented as tutorial chapters on topics such as Boosting, Data Mining, Kernel Methods, Logic, Reinforcement Learning, and Statistical Learning Theory. The papers provide an in-depth overview of these exciting new areas, contain a large set of references, and thereby provide the interested reader with further information to start or to pursue his own research in these directions. Complementary to the book, a recorded video of the presentations during the Summer School can be obtained at http://mlg. anu. edu. au/summer2002 It is our hope that graduate students, lecturers, and researchers alike will ?nd this book useful in learning and teaching Machine Learning, thereby continuing the mission of the Summer School. Canberra, November 2002 Shahar Mendelson Alexander Smola Research School of Information Sciences and Engineering, The Australian National University Thanks and Acknowledgments We gratefully thank all the individuals and organizations responsible for the success of the workshop.

• Algorithms
• Boosting
• algorithm
• kernel method
• learning
• learning theory
• machine learning
• reinforcement learning
• algorithm analysis and problem complexity

• RSISE, The Australian National University, Canberra, Australia

  Shahar Mendelson

• Research School for Information Sciences and Engineering, The Australian National University, Canberra, Australia

  Alexander J. Smola