Vorlesung Practical Machine Learning
Dozent: Prof. Dr. Sven Mayer
Übungsleitung: Jesse Grootjen, Jan Leusmann
Umfang: 2 SWS Vorlesung, 2 SWS Übung
ECTS credits: 6
Sprache: Englisch
Modul: Vertiefende Themen für Master Medieninformatik, Informatik und MCI
Kapazität: max. 50
Termine und Ort
- Vorlesung:
Termin: Do, 10-12 c.t.
Ort: Thalkirchner Str.36 - Theoret. Hörsaal 151
Erste Vorlesung: 20.04.2023 - Übung:
Termin:Mi, 14-16 c.t.
Ort: Thalkirchner Str.36 - Theoret. Hörsaal 151
Erste Vorlesung: 05.05.2023
Aktuelles
- 01.03.2023: You can now enroll for the course via Moodle.
- 07.02.2023: Diese Seite befindet sich im Aufbau, Änderungen vorbehalten.
Empfohlene Vorkenntnisse
The course is designed for senior master students who have taken those following courses (or have equivalent knowledge):
- Vorlesung Mensch-Maschine-Interaktion
- Machine Learning, e.g. Machine Learning course
- Vorlesung Introduction to Intelligent User Interfaces (IUI)
Lehrplan
The goal of this course is to teach the theoretical and practical skills needed to build novel intelligent user interfaces. In detail, the course teaches the fundamental steps of training, deploying, and testing novel intelligent user interfaces using machine learning (ML). Here, we will focus on neuronal networks while using traditional machine learning approaches (e.g., SVN, Random Forest) only as a baseline. During the course, students will learn how to collect data, train ML models, and evaluate the new models based on the extended User-Centered Design process for deep learning.
Over the course of the semester, students will build novel interfaces and present intermediate milestones throughout the tutorials. One group project (in groups up to four) has to be presented during the final presentation sessions. Before developing a new novel interface, the tutorials will also be used to learn the lecture topics' practical side using hands-on exercises. Here, students will learn how to train, deploy, and validate models based on a set of showcase examples.
In summary, this lecture is a practical oriented course that teaches the theoretical and practical skills to train neuronal networks to build intelligent user interfaces from scratch.
Vorlesungen
| Datum | Thema |
|---|---|
| 20.04.2023 | Lecture 01: Organization & Introduction |
| 27.04.2022 | Entfält |
| 04.05.2023 | Lecture 02: Supervised vs. Unsupervised Learning |
| 11.05.2023 | Guest Lecture by Prof. Chris Harrison from Carnegie Mellon University, USA |
| 18.05.2022 | Feiertag |
| 25.05.2023 | Lecture 04: Introduction Neural Networks Lecture 05: Advanced Neural Networks |
| 01.06.2023 | Lecture 06: Evaluating Neural Networks Lecture 07: Trainings Strategies |
| 08.06.2022 | Feiertag |
| 15.06.2023 | Lecture 08: Recurrent Neural Network (RNN) & Long Short-Term Memory (LSTM) |
| 22.06.2023 | Lecture 09: Generative Adversarial Networks (GANs) |
| 29.06.2023 | Lecture 10: Reinforcement Learning |
| 06.07.2023 | Lecture XX: TBA |
| 13.07.2023 | Open Discussion How to give a great project presentation Q'n'A: Exam preparation Individual Help for Projects |
| 20.07.2023 | Abschlusspräsentationen |
Übungen
| Datum | Thema |
|---|---|
| 05.05.2023 | Organization Lecture 03: Full Practical Neural Network Walkthrough |
| 10.05.2023 | Exercise 01: Recording your own data |
| 19.05.2023 | Feiertag |
| 17.05.2023 | Live Coding Session: Deploying Models to Mobile Devices (Android) Exercise 02: Clearing your data and training the first model (2 weeks) |
| 31.05.2023 | Project Ideation Exercise 03: Training an improved model based on a large dataset (1 week) |
| 09.06.2023 | Feiertag |
| 14.06.2023 | Project Pitches: Show Current Project Status |
| 21.06.2023 | Individual Help for Projects |
| 28.06.2023 | Individual Help for Projects |
| 05.07.2023 | Individual Help for Projects |
| 12.07.2023 | Individual Help for Projects |
| 19.07.2023 | Final Presentation |
Klausur
Die Prüfung und Note für das Fach Practical Machine Learning setzen sich aus zwei Teilen zusammen:
- Ihr praktisches Projekt inkl. der Abschlusspräsentation (1/2 der Note)
- Eine Prüfung über die Inhalte der Vorlesung und der Übung (1/2 der Note)
- Hinweiß: Für das bestehen des Kurses müssen beide Teile unabhänging voneinander bestanden werden.
Die Termine für die Prüfungen sind wie folgt:
- Die vorrauslich Prüfung werden am TBA stattfinden.
- Die Abschlusspräsentationen der praktischen Projekte finden am TBA statt während der Übungs- Vorlesungszeiten statt.
- Die Anmeldung zur Prüfung erfolgt auf Moodle.
