Fundamentals of Machine Learning

PD Dr. Ullrich Köthe, WS 2017/18

This lecture belongs to the Master in Physics (specialisation Computational Physics, code "MVSpec") and the Master of Applied Informatics (code "IFML") programs, but is also open for students of Scientific Computing and anyone interested.

Solid basic knowledge in linear algebra, analysis (multi-dimensional differentiation and integration) and probability theory is required.

Summary:

Machine learning is one of the most promising approaches to address difficult decision and regression problems under uncertainty. The general idea is very simple: Instead of modeling a solution explicitly, a domain expert provides example data that demonstrate the desired behavior on representative problem instances. A suitable machine learning algorithm is then trained on these examples to reproduce the expert's solutions as well as possible and generalize it to new, unseen data. The last two decades have seen tremendous progress towards ever more powerful algorithms, and the course will cover the fundamental ideas from this field.

Dates:

Lecture Wednesdays 14:15-15:45 Hörsaal Mathematikon (only 18. Oct)
Hörsaal COS, INF 360 (starting 25. Oct)
Lecture Fridays 11:15-12:45
12:30-14:00
Hörsaal Mathematikon
Hörsaal Chemie, INF 252 East
Tutorials Wednesdays
Fridays
12:30-14:00
11:00-12:15
Hörsaal Chemie, INF 252 West
Hörsaal Mathematikon, INF 205

Please register for the lecture via MÜSLI.

Homework Assignments:

Please download homework assignments and upload your solutions via Moodle.