252-0526-00L  Statistical Learning Theory

SemesterSpring Semester 2015
LecturersJ. M. Buhmann
Periodicityyearly recurring course
Language of instructionEnglish



Catalogue data

AbstractThe course covers advanced methods of statistical learning :
PAC learning and statistical learning theory;variational methods and optimization, e.g., maximum entropy techniques, information bottleneck, deterministic and simulated annealing; clustering for vectorial, histogram and relational data; model selection; graphical models.
ObjectiveThe course surveys recent methods of statistical learning. The fundamentals of machine learning as presented in the course "Introduction to Machine Learning" are expanded and in particular, the theory of statistical learning is discussed.
Content# Boosting: A state-of-the-art classification approach that is sometimes used as an alternative to SVMs in non-linear classification.
# Theory of estimators: How can we measure the quality of a statistical estimator? We already discussed bias and variance of estimators very briefly, but the interesting part is yet to come.
# Statistical learning theory: How can we measure the quality of a classifier? Can we give any guarantees for the prediction error?
# Variational methods and optimization: We consider optimization approaches for problems where the optimizer is a probability distribution. Concepts we will discuss in this context include:

* Maximum Entropy
* Information Bottleneck
* Deterministic Annealing

# Clustering: The problem of sorting data into groups without using training samples. This requires a definition of ``similarity'' between data points and adequate optimization procedures.
# Model selection: We have already discussed how to fit a model to a data set in ML I, which usually involved adjusting model parameters for a given type of model. Model selection refers to the question of how complex the chosen model should be. As we already know, simple and complex models both have advantages and drawbacks alike.
# Reinforcement learning: The problem of learning through interaction with an environment which changes. To achieve optimal behavior, we have to base decisions not only on the current state of the environment, but also on how we expect it to develop in the future.
Lecture notesno script; transparencies of the lectures will be made available.
LiteratureDuda, Hart, Stork: Pattern Classification, Wiley Interscience, 2000.

Hastie, Tibshirani, Friedman: The Elements of Statistical Learning, Springer, 2001.

L. Devroye, L. Gyorfi, and G. Lugosi: A probabilistic theory of pattern recognition. Springer, New York, 1996
Prerequisites / NoticeRequirements:

basic knowledge of statistics, interest in statistical methods.

It is recommended that Introduction to Machine Learning (ML I) is taken first; but with a little extra effort Statistical Learning Theory can be followed without the introductory course.

Performance assessment

Performance assessment information (valid until the course unit is held again)
Performance assessment as a semester course
ECTS credits4 credits
ExaminersJ. M. Buhmann
Typesession examination
Language of examinationEnglish
RepetitionThe performance assessment is only offered in the session after the course unit. Repetition only possible after re-enrolling.
Mode of examinationoral 15 minutes
This information can be updated until the beginning of the semester; information on the examination timetable is binding.

Learning materials

 
Main linkInformation
Only public learning materials are listed.

Courses

NumberTitleHoursLecturers
252-0526-00 VStatistical Learning Theory2 hrs
Mon14-16HG G 5 »
J. M. Buhmann
252-0526-00 UStatistical Learning Theory1 hrs
Mon16-17HG G 5 »
J. M. Buhmann

Groups

No information on groups available.

Restrictions

There are no additional restrictions for the registration.

Offered in

ProgrammeSectionType
Certificate of Advanced Studies in Computer ScienceFocus Courses and ElectivesWInformation
Electrical Engineering and Information Technology MasterRecommended SubjectsWInformation
Electrical Engineering and Information Technology MasterRecommended SubjectsWInformation
Computer Science MasterFocus Elective Courses Computational ScienceWInformation
Computer Science MasterFocus Elective Courses Visual ComputingWInformation
Computational Science and Engineering MasterCompensatory CoursesWInformation
Computational Science and Engineering MasterElectivesWInformation
Robotics, Systems and Control MasterArtificial IntelligenceWInformation
Statistics MasterStatistical and Mathematical CoursesWInformation