Search:
Lehrstuhl  |  Institut  |  Fakultät  |  LMU
print

Machine Learning im SS 2017


The lecture is given in English.


News

  • 16.08.17: The opportunity to have insight your own exam is scheduled for
    Thursday, 24.08.2017, 1pm - 2pm, in the Oettingenstr. 67, room 157.
    If you have earnest issues with the date write an email to Janina Sontheim till the 23.08.17 to get a second chance to see your exam. Emails after this date can not be considered.
  • Please note the guidelines for the final exam!
  • Today, 22.06., the tutorial will not take place.
  • Changes for the lecture on the 31th of May: time: 8:00-10:00, place: main building, room B201
  • The final exam is going to take place on Monday, 07th of August 2017, 4-6 pm (s.t.).
  • The location for the lecture has changed. The new location is in the Pettenkoferstr. 14.

Topic

Machine Learning is a data-driven approach for the development of technical solutions. Initially motivated by the adaptive capabilities of biological systems, machine learning has increasing impact in many fields, such as vision, speech recognition, machine translation, and bioinformatics, and is a technological basis for the emerging field of Big Data.

The lecture will cover:

  • Supervised learning: the goal here is to learn functional dependencies for classification and regression. We cover linear systems, basis function approaches, kernel approaches and neural networks. We will cover the recent developments in deep learning which lead to exciting applications in speech recognition and vision.
  • Unsupervised Learning: the goal here is to compactly describe important structures in the data. Typical representatives are clustering and principal component analysis
  • Graphical models (Bayesian networks, Markov networks), which permit a unified description of high-dimensional probabilistic dependencies
  • Reinforcement Learning as the basis for the learning-based optimization of autonomous agents
  • Some theoretical aspects: frequentist statistics, Bayesian statistics, statistical learning theory

The technical topics will be illustrated with a number of real-world applications.


Organisation


Time and Location

Event Time Location Start
Lecture Wed 9.00 c.t. - 12.00 p.m. Room F102, großer Hörsaal Physiologie (Pettenkoferstr. 14) 26.04.2017
Exercise
Thu, 14.00 - 16.00 p.m. Room 020 (Amalienstr. 73A)
04.05.2017

Thu, 16.00 - 18.00 p.m. Room M105 (Geschwister-Scholl-Platz 1)
04.05.2017

Planung

Lecture Exercise
Date Topic Date Sheet
26.04.17 Introduction 27.04.17 -
03.05.17 Perceptron (update p.24), Linear Regression, Linear Algebra 04.05.17 Exercise Sheet 1 updated
10.05.17 Basis Functions (updated), Neural Networks (updated) 11.05.17 Exercise Sheet 2
Exercise 2-1.ipynb Exercise 2-2.ipynb
17.05.17 Deep Learning, by Dr. Denis Krompass 18.05.17 Exercise Sheet 3
Suggested solution
24.05.17 Deep Learning Time Series 25.05.17 Christi Himmelfahrt
31.05.17 References for Reinforcement Learning, by Dr. Michel Tokic
8:00-10:00, in the main building, room B201
01.06.17 Exercise Sheet 4
Exercise 4-2.ipynb
Suggested solution
07.06.17 Kernels, Probability, Frequentists Bayesians, Linear Classifiers 08.06.17 Exercise Sheet 5
Exercise 5-1.ipynb Exercise 5-2.ipynb
MLP, CNN
Suggested solution
14.06.17 PCA and Factorisation, by Dr. Clemens Otte
Python-Example References
15.06.17 Fronleichnam
21.06.17 Frequentists versus Bayes, Linear Classifiers 22.06.17 -
28.06.17 Forecasting with Neural Networks, by Dr. Stefanie Vogl 29.06.17 Exercise Sheet 6
Suggested solution
05.07.2017 Support Vector Machine, Model Comparison 06.07.17 Exercise Sheet 7
body_sizes.txt
Suggested solution
12.07.17 Bayesian Networks 13.07.17 Exercise Sheet 8
Suggested solution
19.07.17 Bayesian Networks (cont.)
different time and room:
8:00-10:00, Geschwister-Scholl-Platz 1, B201
20.07.17 Exercise Sheet 9
Suggested Solution
26.07.17 (short) review of the discussed topics and question time 27.07.17 Exercise Sheet 10
Suggested Solution

Übungsbetrieb

  • Zur Vertiefung der Vorlesung werden 2-stündige Übungen angeboten, in denen die vorgestellten Verfahren weiter erläutert und an praktischen Beispielen veranschaulicht werden. Da es sich mitunter um Programmieraufgaben handelt, ist eine vorherige Vorbereitung des aktuellen Übungsblattes erwünscht um Fragen diesbezüglich besser beantworten zu können.

Klausur / Exam

  • Guidelines for the final exam!
  • Date: 07th of August 2017, 4pm - 6pm
  • Location: Geschwister-Scholl-Platz 1, main building, room B201 and M 218
  • Distribution according to your last name:
    B 201: A - M
    M 218: N - Z
  • Registration is required and available via UniWorX
  • The lectures from the following dates will not be tested in the final exam: 17.05., 31.05., 28.06.2017.
  • Please note that there is no 2nd exam!

Nützliche Links


Vorhergehende Semester

SS 16, SS 15, SS 14, SS 13, SS 12, SS 11, SS 10, SS 09, SS 08, SS 07, SS 06, SS 05, SS 04

blank