Hands-on Deep Learning WS 2024/25
Time and Place
Block course offered every Winter & Summer Semester
WS 2024/25: 10.03.-18.03, 9:00-16:30
Place: MW 0234
A regular presence is required.
Program
M.Sc. Lab Course (Hochschulpraktikum)
Language: English
4 ECTS, 4 PR
Please sign up using the TUMonline matching system
Literature
Suggested literature will be given in the course material.
Exam
Type: group project report and presentation
Time and Place: last session
Grade Breakdown
70% project report
30% project presentation
Highly recommended prerequisites are experience with Python and a prior course on machine learning. Please deregister from TUMonline if you do not plan to attend or lack the prerequisites to give other students a chance to take the spot.
For more information on the registration procedure, please visit the Wiki page: https://collab.dvb.bayern/display/TUMedschoolofficeintern/Hochschulpraktika+EN
What's this course about?
Get hands-on experience with deep learning algorithms. If you want to learn how autonomous vehicles perceive their environment or how to generate deep fakes, this is the course for you! We will cover deep neural networks, convolutional networks, recurrent nets, autoencoders and deep generative methods. For a more detailed description see the module handbook.
How does it work?
Tricks of the trade
In the 1st hour of each session, the topic is introduced by the TA with slides. Key concepts are discussed, and examples are given from scientific and everyday life.
Learn by doing
In each session, we will learn a different deep learning method by applying it to a concrete problem. Downloadable jupyter notebooks will give you step-by-step instructions to the solution. The solutions will be in Numpy and PyTorch.
Learn with others
Problems can be solved in small teams. A collection of questions on Moodle allows you to learn from and help your fellow students.
Team project
Form a team of two and select a project from our list or propose your own.
Project Report
Summarize your main findings in a project report.
Project Presentation
Present your project to your fellow students.
Questions
For any organizational questions, write an email to the head TA.
Online Support
Need help with exercises? You didn't quite understand the lectures? Post on Moodle and get fast feedback.