|
⇤ ← Revision 1 as of 2012-05-15 12:42:16
Size: 1810
Comment:
|
Size: 1806
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 5: | Line 5: |
| || '''Organizers:''' || [[http://www.ml.tu-berlin.de/menue/mitglieder/franz_kiraly/|Dr. Dr. Franz Király]], [[http://www-irm.mathematik.hu-berlin.de/~larsen/|Dr. Paul Larsen]] || | || '''Organizers:''' || [[http://www.ml.tu-berlin.de/menue/mitglieder/franz_kiraly/|Dr. Franz Király]], [[http://www-irm.mathematik.hu-berlin.de/~larsen/|Dr. Paul Larsen]] || |
Reading Seminar on Algebraic Geometry and Singular Learning Theory
Time: |
Friday, 10:00 - 12:00 |
Room: FR 6046 |
|
Organizers: |
Summary
Singular Learning Theory is the study of singular parametric estimation, where naive adaptations of classical learning and model selection methods like Max-Likelihood, Bayes Learning, AIC, BIC fail. As virtually all meaningful and practically relevant learning machines like Neural Networks, Mixture Models, Hidden Markov Models or Boltzmann Machines are singular, the analysis of their singular properties is of high practical relevance. Sumio Watanabe has developed generalizations of Bayes Learning Theory and Bayes Model Selection for the singular case; the aim of this seminar is the study of his work and its ramifications.
Prerequisites
Knowledge in Algebraic Geometry, Singularity Theory, Parametric Statistics and Bayes Estimation Theory is useful, but not necessary; all relevant basics will be discussed in the course.
Schedule
The topic list refers to the book Algebraic geometry and statistical learning theory, by S. Watanabe.
Date |
Topic |
Discussion leader |
20 April 2012 |
Introduction: Algebraic Geometry and Singular Learning Theory |
Duncan Blythe and Paul Larsen |
11 May 2012 |
Chapter 1: Learning Theory and Singular Parametric Models |
Franz Király |
25 May 2012 |
Chapter 1: Singular Examples, Learning and Generalization Error, Main Formulas |
Franz Király |