Course in Foundations of Machine Learning
General Information
| Lecturer | Jun.-Prof. Dr. Martin Potthast |
| Lab Advisors | Lukas Gienapp, Niklas Deckers |
| Workload | 2 SWS Lecture, 1 SWS Lab |
| Lecture | Tuesday, 15:15 - 16:45, HS 1 (Hörsaalgebäude). |
| Lab | There are 4 groups (i.e. repetitions of the lab). 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 (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. For that, you will also be able to make use of the videos that we will provide. The lab sessions will be done in a flipped classroom format. This only works if you are well prepared. 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 26.10.2022 19.10.2022 25.10.2022 18.10.2022 2 09.11.2022 02.11.2022 08.11.2022 01.11.2022 3 30.11.2022 23.11.202229.11.2022 22.11.2022 4 14.12.2022 07.12.202213.12.2022 06.12.2022 5 18.01.202311.01.2023 17.01.202310.01.2023 6 01.02.202325.01.2023 31.01.202324.01.2023 - 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 25.01.2023.
- It will be discussed in the lecture slot on 31.01.2023.
- The exam will take place on 06.02.2023, 12:30, at Auditorium Maximum (Audimax).
- 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
- The rewrite exam (Nachklausur) will take place on 28.03.2023, 12:30, at HS 3 (Hörsaalgebäude).
Lecturenotes
- Machine Learning » Introduction » Organization, Literature [video]
- Machine Learning » Introduction » Learning Tasks [video]
- Machine Learning » Introduction » Elements of Machine Learning [video]
-
Machine Learning »
Introduction »
Syntax & Model Overview
- Machine Learning » Machine Learning Basics » Concept Learning [video]
- Machine Learning » Machine Learning Basics » From Regression to Classification [video]
-
Machine Learning »
Machine Learning Basics »
Evaluating Effectiveness [video]
- Machine Learning » Linear Models » Logistic Regression [video]
- Machine Learning » Linear Models » Overfitting and Regularization [video]
-
Machine Learning »
Linear Models »
Gradient Descent [video]
- Machine Learning » Bayesian Learning » Probability Basics [video]
- Machine Learning » Bayesian Learning » Bayes Classifier [video]
-
Machine Learning »
Bayesian Learning »
Frequentist versus Subjectivist
- Machine Learning » Decision Trees » Decision Trees Basics [video]
- Machine Learning » Decision Trees » Impurity Functions [video 1] [video 2]
- Machine Learning » Decision Trees » Decision Trees Algorithms [video]
-
Machine Learning »
Decision Trees »
Decision Trees Pruning [video]
- Machine Learning » Neural Networks » Perceptron Learning [video]
- Machine Learning » Neural Networks » Multilayer Perceptron [video]
- Machine Learning » Neural Networks » Advanced MLPs [video]
Lab
The specific dates of the lab sessions can be found here: Organization.
Topic 1: Python and Maths Basics
- Relevant lectures: Until Introduction > Learning Tasks
- Theoretical exercises
- Practical exercises
- Lab exercises (will be done during the lab session)
Topic 2: Evaluation
- Material will be published on: 25.10.2022
- Relevant lectures: Until Machine Learning Basics > Evaluating Effectiveness
- Theoretical exercises
- Practical exercises
- Lab exercises (will be done during the lab session)
Topic 3: Linear Models
- Material will be published on: 15.11.2022
- Relevant lectures: Until Linear Models > Overfitting & Regularization
- Theoretical exercises
- Practical exercises
- Lab exercises (will be done during the lab session)
Topic 4: Bayesian Classification
- Material will be published on: 29.11.2022
- Relevant lectures: Until Bayesian Learning > Bayes Classifier
- Theoretical exercises
- Practical exercises
- Lab exercises (will be done during the lab session)
Topic 5: Tree-Based Classification
- Material will be published on: 05.01.2023
- Relevant lectures: Until Decision Trees > Pruning
- Theoretical exercises
- Practical exercises
- Lab exercises (will be done during the lab session)
Topic 6: Neural Networks
- Material will be published on: 17.01.2023
- Relevant lectures: Until Neural Networks > Multilayer Perceptron
- Theoretical exercises
- Practical exercises
- Lab exercises (will be done during the lab session)