Joachim M. Buhmann: Catalogue data in Spring Semester 2020
|Prof. Dr. Joachim M. Buhmann
|Computer Science (Information Science and Engineering)
Institut für Maschinelles Lernen
ETH Zürich, OAT Y 13.2
|+41 44 632 31 24
|+41 44 632 15 62
|2V + 1U
|L. Haug, J. M. Buhmann
|The course covers the fundamental concepts of Shannon's information theory.
The most important topics are: Entropy, information, data compression, channel coding, codes.
|The goal of the course is to familiarize with the theoretical fundamentals of information theory and to illustrate the practical use of the theory with the help of selected examples of data compression and coding.
|Introduction and motivation, basics of probability theory, entropy and information, Kraft inequality, bounds on expected length of source codes, Huffman coding, asymptotic equipartition property and typical sequences, Shannon's source coding theorem, channel capacity and channel coding, Shannon's noisy channel coding theorem, examples
|T. Cover, J. Thomas: Elements of Information Theory, John Wiley, 1991.
D. MacKay, Information Theory, Inference and Learning Algorithms, Cambridge University Press, 2003.
C. Shannon, The Mathematical Theory of Communication, 1948.
|Statistical Learning Theory
|3V + 2U + 1A
|J. M. Buhmann, C. Cotrini Jimenez
|The course covers advanced methods of statistical learning:
- Variational methods and optimization.
- Deterministic annealing.
- Clustering for diverse types of data.
- Model validation by information theory.
|The course surveys recent methods of statistical learning. The fundamentals of machine learning, as presented in the courses "Introduction to Machine Learning" and "Advanced Machine Learning", are expanded from the perspective of statistical learning.
|- Variational methods and optimization. We consider optimization approaches for problems where the optimizer is a probability distribution. We will discuss concepts like maximum entropy, information bottleneck, and deterministic annealing.
- Clustering. This is the problem of sorting data into groups without using training samples. We discuss alternative notions of "similarity" between data points and adequate optimization procedures.
- Model selection and validation. This refers to the question of how complex the chosen model should be. In particular, we present an information theoretic approach for model validation.
- Statistical physics models. We discuss approaches for approximately optimizing large systems, which originate in statistical physics (free energy minimization applied to spin glasses and other models). We also study sampling methods based on these models.
|A draft of a script will be provided. Lecture slides will be made available.
|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 / Notice
|Knowledge of machine learning (introduction to machine learning and/or advanced machine learning)
Basic knowledge of statistics.
|Doctoral Seminar Machine Learning (FS20)
Only for Computer Science Ph.D. students.
This doctoral seminar is intended for PhD students affiliated with the Institute for Machine Learning. Other PhD students who work on machine learning projects or related topics need approval by at least one of the organizers to register for the seminar.
|J. M. Buhmann, T. Hofmann, A. Krause, G. Rätsch
|An essential aspect of any research project is dissemination of the findings arising from the study. Here we focus on oral communication, which includes: appropriate selection of material, preparation of the visual aids (slides and/or posters), and presentation skills.
|The seminar participants should learn how to prepare and deliver scientific talks as well as to deal with technical questions. Participants are also expected to actively contribute to discussions during presentations by others, thus learning and practicing critical thinking skills.
|Prerequisites / Notice
|This doctoral seminar of the Machine Learning Laboratory of ETH is intended for PhD students who work on a machine learning project, i.e., for the PhD students of the ML lab.
|Foundations of Data Science Seminar
|P. L. Bühlmann, A. Bandeira, H. Bölcskei, J. M. Buhmann, T. Hofmann, A. Krause, A. Lapidoth, H.‑A. Loeliger, M. H. Maathuis, N. Meinshausen, G. Rätsch, C. Uhler, S. van de Geer, F. Yang