Machine Learning (Maschinelles Lernen)

Machine  learning  is  a  rapidly  developing  research  field  that  gives computer systems the ability to learn with data and to act without being explicitly programmed.  Modern applications of machine learning techniques can be found in self-driving cars, image and speech recognition, virtual personal assistance, and human genome decoding. Machine learning is so pervasive today that people use it dozens of times a day without knowing it, e.g.  traffic jams predictions, social media services, email spam and malware filtering, online customer support, search engine results refining, and product recommendations. In this class, you will learn about the most effective machine learning techniques and the underlying mathematical theory.

The course Machine Learning gives an overview of the basic concepts, techniques, and algorithms in modern machine learning, with a special emphasis on Reinforcement Learning.  Also,  it aims to provide rigorous mathematical foundations of the covered methods.  During exercises the students will have the opportunity to test the theoretical ideas into practice in form of a group seminar project.

Preliminaries: Introduction to probability theory and methods of statistics.

Supervised / Unsupervised Learning: Basic concepts and models. Bayes classifiers.  Logistic regression.  Perceptron.  Support vector machines.  Clustering.  Factor analysis.

Deep Learning: Artificial neural networks architecture.  Forward- and backpropagation.

Reinforcement Learning and Control: Markov decision  processes.  Bellman equations.  Q-learning.

• Goodfellow, I., Bengio, Y., Courville, A.:  “Deep Learning”. Cambridge:  MIT Press, 2016.
• Murphy, K.:  “Machine Learning:  A probabilistic perspective”. Cambridge:  MIT Press, 2012.
• Sutton, R.S., Barto, A.G.:  “Reinforcement Learning:  An introduction”. Cambridge:  MIT Press, 1998.

Prof. Dr.-Ing. Naim Bajcinca
naim.bajcinca(at)mv.uni-kl.de
+49 631/205-3230
Gebäude 42, Raum 262
Sprechstunde: nach Vereinbarung

Übungsleiter

Dr. Sandesh Hiremath
sandesh.hiremath(at)mv.uni-kl.de
Gebäude 65, Raum 420
Sprechstunde: nach Vereinbarung

Thursdays, 12:15-13:45
Building 46, Room 260
KIS-Entry
 

Written examination
Date: To be announced!
Credit points: 5 ECTS

KIS-entry

Abstraction capability
Control and Optimization
Higher Mathematics
Programming skills / Python

Download as PDF