Course in Foundations of Machine Learning

General Information

Lecturer Prof. Dr. Martin Potthast
Lab Advisors Lukas Gienapp, Niklas Deckers
Workload 2 SWS Lecture, 1 SWS Lab
Language Materials in English; lecture and lab in German; exam in German (but writing answers in English is possible).
Requirements See below: Requirements.
Lecture Tuesday, 13:15 - 14:45, HS 2 (Hörsaalgebäude), starting 10.10.2023.
Lab Each student is part of one of 4 groups (A, B, C or D), which determines the time slot for their lab session (Übung).
A and B: On selected Wednesdays, 11:15 - 12:45, Felix-Klein-Hörsaal (Paulinum, 5th floor).
C and D: On selected Tuesdays, 11:15 - 12:45, Felix-Klein-Hörsaal (Paulinum, 5th floor).
The specific dates for the 6 sessions can be found below: Organization.
Exam Written exam at the end of the semester.

Organization

  • The lecture will take place in attendance. It will also be recorded and uploaded afterwards.
  • In addition to the lecture, you will be provided with both theoretical and practical exercises. We will not collect or grade these exercises, but provide you with solutions and helpful tutorial videos (released at the same time). Nevertheless, you will still need to solve the exercises on your own/with a partner. You are responsible for your own learning success.
  • We expect you to have studied the lecture, solved the exercises and reviewed the solutions before the corresponding lab session takes place. The lab sessions will be done in a flipped classroom format. This only works if you are well prepared. Please bring a laptop, tablet or smartphone to participate. The lab sessions will not be streamed or recorded.
    The dates of your group's lab sessions can be found in the following table:
    Topic Group A Group B Group C Group D
    1 25.10.2023 18.10.2023 24.10.2023 17.10.2023
    2 08.11.2023 01.11.2023 14.11.2023 07.11.2023
    3 29.11.2023 15.11.2023 28.11.2023 21.11.2023
    4 13.12.2023 06.12.2023 12.12.2023 05.12.2023
    5 10.01.2024 03.01.2024 09.01.2024 19.12.2023
    6 24.01.2024 17.01.2024 23.01.2024 16.01.2024

    We might be forced to close single groups (A, B, C, D) during the semester due to a lack of attendance. Remaining participants will then be asked to join another group.
  • Please also communicate with your fellow students to exchange about the course topics, the exercises and solution approaches.
    • Lecture website - materials and announcements will be uploaded on this website.
    • Email - important announcements will be sent out via email to students that are officially enrolled via AlmaWeb. Please notify Niklas Deckers immediately if you did not receive the welcome email at the start of the semester.
    • Discord - you are invited to engage in discussions with your fellow students. We provide a Discord server that you are invited to join. The link will be provided in the welcome email.

Exam

  • There will be a take-home mock exam that we are planning to release on 23.01.2024.
  • It will be discussed in the lecture slot on 30.01.2024.
  • The exam will take place on 06.02.2024, start at 12:45, in Audimax.
  • The rewrite exam (Nachklausur) will take place on 26.03.2024, start at 11:00, in HS 1 (Hörsaalgebäude).
  • The exam will be in German, but you are also allowed to write your answers in English.
  • Please remember to bring your passport/Personalausweis and your student ID.
  • You are allowed to bring a handwritten sheet (DIN A4, one side only) with useful information into the exam. It must be written by hand by yourself. The sheet will be collected together with the exam at the end of the exam.
  • You are also allowed to bring a non-programmable calculator.
  • If needed (international students), you may bring a dictionary.
  • Mock exam, Mock exam solution (updated)

Requirements

Prerequisites for this course are the basic modules about algorithms and data structures, theoretical computer science and mathematics. We will use Python as a programming language.
It might be helpful to refresh the following topics as their use will be required in the course. This list might be incomplete.
  • Mathematical set notation
  • Boolean formulas
  • Matrix multiplication and transposition, matrix-vector multiplication
  • Partial derivatives, rules of derivation, Taylor formula
  • Straight line equation: Formulating the equation, drawing and reading a plot; quadratic functions
  • Laws of exponents, laws of logarithms
  • Probabilities: Product rule, conditional probabilities, independence, total probability, Bayes Theorem

Lecturenotes

Logbook

  • 10.10.2023: Until the end of Introduction > Elements of Machine Learning
  • 17.10.2023: Until the end of Machine Learning Basics > Concept Learning
  • 24.10.2023: Until slide ML:II-155 in Machine Learning Basics > Evaluating Effectiveness
  • 07.11.2023: Until slide ML:III-47 in Linear Models > Logistic Regression
  • 14.11.2023: Until the end of Linear Models > Gradient Descent
  • 21.11.2023: Until the end of Bayesian Learning > Bayes Classifier
  • 28.11.2023: Until slide ML:VI-52 in Decision Trees > Impurity Functions
  • 05.12.2023: Until the end of Decision Trees > Decision Trees Pruning
  • 12.12.2023: Christmas exercise [notebook (Colab)] [recording]
  • 09.01.2023: Until slide ML:IV-76 in Neural Networks > Multilayer Perceptron
  • 16.01.2023: Until the end of Neural Networks > Advanced MLPs
  • 23.01.2023: Q&A session [transcript]
  • 30.01.2023: Discussion of the mock exam and the Christmas exercise

Lab

The specific dates of the lab sessions can be found here: Organization.

Topic 1: Intro, Python and Maths Basics

Topic 2: Concept Learning & Evaluation

Topic 3: Linear Models

Topic 4: Bayesian Classification

Topic 5: Tree-Based Classification

Topic 6: Neural Networks