Machine Learning
This web page gives information on the lecture 'Machine Learning' which is held during winter term 2016/2017 by Andreas Nürnberger. It will be constantly updated during the course.
The course provides an introduction to the principles, techniques, and applications of Machine Learning. Topics covered include among others:
- value functions
- concept spaces and concept learning
- instance based learning
- clustering
- decision trees
- neural networks
- Bayesian learning
- reinforcement learning
- association rule learning
- genetic algorithms
Course Schedule and Room Assignments
| Time | Start | Room | |
| Lecture | Tuesday 3:15 - 4:45pm | 11.10.2016 | |
| Exercises (1st group) | Monday 3:15 - 4:45pm | 17.10.2016 | G22A-120 (40 people) |
| Exercises (2nd group) | Monday 1:15 - 2:45pm | 17.10.2016 | G22A-105 (40 people) |
| Exercises (3rd group) | Tuesday 1:15 - 2:45pm | 18.10.2016 | G22A-113 (24 people) |
| Exam (Update!) | Thursday 1:00 - 3:00pm! | 09.02.2017 | G29-307 |
Post-Exam Review
If you want to have a look at your exam, in order to know, what you have made right and wrong, please contact me at marcus.thiel@ovgu.de.
Starting from the 13th of March until the 10th of April, I am not available. If you still want to see your exam during that period of time, please schedule an appointment with my colleague, Johannes Schwerdt, at johannes.schwerdt@ovgu.de.
Registration
Registration for the individual groups is done in the exercises themselves.
Course Staff
If you have any questions concerning the lectures or assignments please contact (if possible by email):
Requirements for the Written Exam and the 'Schein'
All students are required to participate in the exercise classes. Every week, there will be an assignment sheet that will be handed out one week in advance. This sheet has to be prepared by every student and will be discussed in class. There are two different types of assignments: questions of understanding and programming assignments. The programming assignments can be solved in small groups of up to three students and must be sent in before the respective class. Prerequisites for a written exam and a 'Schein' is fulfillment of the following criteria:
- Gaining at least 1/2 of all programming points
- Solving at least 2/3 of all questions of understanding
- Presenting at least 2 solutions in class.
The exam will be written. For the 'Schein', you have to write the exam as well. The exam will be on the 9th of February 2017 in the room G29-307 (FIN-Hörsaal).
General remarks concerning the exam:
- The main focus will be on the topics, that were also discussed in the exercises.
- Theoretical questions (knowledge and understanding) will be from all parts of the lecture.
- Practical tasks will be similar to the exercise assignments.
Materials
Lecture Slides
- Course Information
- Introduction
- Concept Learning
- Decision Tree Learning
- Cluster Analysis (updated 22.11.2016)
- Artificial Neural Networks
- Bayesian Learning
- Reinforcement Learning
- Instance-based Learning (Update 18.01.2017)
- Association Rule Learning
Assignment Sheets
- Assignment Sheet 1 (TicTacToe scheme)
- Assignment Sheet 2 (due by the 24/25th of October 2016)
- Assignment Sheet 3 (due by the 7/8th of November 2016)
- Assignment Sheet 4 (due by the 14/15th of November 2016)
- Assignment Sheet 5 (due by the 21st/22nd of November 2016)
- Assignment Sheet 6 (due by the 28/29th of November 2016)
- Assignment Sheet 7 (due by the 5th/6th of December 2016)
- Assignment Sheet 8 (due by the 12th/13th of December 2016)
- Assignment Sheet 9 (due by the 9th/10th of January 2017)
- Assignment Sheet 10 (due by the 16th/17th of January 2017)
- Assignment Sheet 11 (due by the 23th/24th of January 2017)
Seminar
Other Resources
- Schedule for the Exercises (updated 14.11.2016)
- Scoring of Programming Assignments
- Scoring of First Programming Assignment (Tic Tac Toe)
- Scoring of Second Programming Assignment (DTs/ID3)
- Scoring of Third Programming Assignment (K-Means)
- Scoring of Fourth and Fifth Programming Assignment (NaiveBayes & kNN)
- Overview of Programming Assignments (updated 14.11.2016)
- TicTacToe Environment v1.3.0 + Source Code
- Car Data (see also the UCI Machine Learning Repository)
- Master Assignments
Literature
- Machine Learning
Tom Mitchell
McGraw-Hill, 1997. - Artificial Intelligence: A Modern Approach
S. Russel and P. Norvig
Prentice Hall, Englewood Cliffs, 2003 - Introduction to Artificial Intelligence (German version: Grundkurs Künstliche Intelligenz)
Wolfgang Ertel
Springer-Verlag London, 2011 (German version: Springer Vieweg, 2013)