Machine Learning
Semester: 
WS 2023 
Type: 
Lecture 
Lecturer: 

Credits: 
V3 + Ü1 (6 ECTS credits) 
Lecture Organization
The following information is preliminary and may change at a later date due to new regulations in the pandemic. We hope for your understanding.

The lecture will take place in presence. For this, we have reserved lecture halls with sufficient capacity to comfortably sit the expected number of participants with an extended distance (at least 1 empty seat between participants in all directions). If the number of registrations further increases beyond that capacity, we have the option to move to a larger lecture hall.

All lectures will be recorded as screencast and will be made available to all lecture participants as a video in the moodle learning room (typically 12 days after the lecture due to the postprocessing effort involved). This way, nobody will have to miss a lecture slot due to potential illness or quarantine periods. If none of those conditions apply, we however strongly recommend attending the lecture in person, as it makes for a more wholesome learning experience.

We will also experiment with transmitting the lecture as a live zoom broadcast from the lecture hall in the spirit of a true hybrid format, but it is unclear whether bandwidth will be sufficient to support this.
Lecture Description
The goal of Machine Learning is to develop techniques that enable a machine to "learn" how to perform certain tasks from experience.
The important part here is the learning from experience. That is, we do not try to encode the knowledge ourselves, but the machine should learn it itself from training data. The tools for this are statistical learning and probabilistic inference techniques. Such techniques are used in many realworld applications. This lecture will teach the fundamental machine learning knowhow that underlies such capabilities. In addition, we show current research developments and how they are applied to solve realworld tasks.
Example questions that could be addressed with the techniques from the lecture include
 Is this email important or spam?
 What is the likelihood that this credit card transaction is fraudulent?
 Does this image contain a face?
Exercises
The class is accompanied by exercises that will allow you to collect handson experience with the algorithms introduced in the lecture.
There will be both pen&paper exercises and practical programming exercises (roughly 1 exercise sheet every 2 weeks). Please submit your solutions electronically through the RWTH Moodle system.
We ask you to work in teams of 23 students.
Literature
The first half of the lecture will follow the book by Bishop. For the second half, we will use the Deep Learning book by Goodfellow as a reference.
 Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006
 Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016
Wherever research papers are necessary for a deeper understanding, we will make them available in RWTH Moodle.
Additional Resources
 Kevin Murphy, Machine Learning  A Probabilistic Perspective, MIT Press, 2012.
Python Resources
 A comprehensive python tutorial which is quite long
 Gives a very basic introduction to python and control loops (A sub topic of the above link)
 This subsection gives an overview of python data structures such as list, dictionaries etc. (Again a subtopic of the above link)
 A basic numpy tutorial
 PyCharm, a Python IDE