Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich



Practical Course: Beyond Deep Learning: Uncertainty Aware Models (10 ECTS)

Summer Semester 2020, TU München

Organizers: Christian Tomani, Yuesong Shen, Prof. Dr. Daniel Cremers

E-Mail: bdluam-ss20@vision.in.tum.de


The Kick-Off meeting takes place on April 22nd at 1-3pm via zoom. The link to the online meeting will be sent to all participants via email.

Please send us an email (bdluam-ss20@vision.in.tum.de) before April 26th with the following template in order to get matched to a project (Subject: "[Project Matching] <firstname> <lastname>"): Template (rename to firstname_lastname.xlsx)

The preliminary meeting took place on February 4th at 4-5pm at 02.09.023: slides are here.

Course Description

Deep learning models nowadays provide state of the art results and set a new standard for many applications, such as speech recognition, computer vision, predicting patients’ states in medicine as well as time series forecasting in finance. However, these models generally lack the ability to correctly estimate uncertainty, which is crucial for real world applications.

This course will be focusing on developing deep learning models with a particular focus on uncertainty awareness. The topics will include:

  • Time series models and post-calibration
  • Bayesian deep learning models
  • Graphical Models
  • Alternative deep models and learning methods
  • Metrics for evaluating uncertainty
  • Real world datasets

We will be tackling real world problems and will be working on open issues in the scientific community.


Participants should have good programming skills and sufficient knowledge on Python programming and tensor operations, as well as experience with a mainstream deep learning framework such as PyTorch or Tensorflow.

Participants should already have a good understanding of basic machine learning and deep learning concepts and models. Especially, they are required to have taken at least one machine learning related course such as:

  • Introduction to Deep Learning
  • Introduction to Machine Learning
  • Machine Learning for Computer Vision
  • Advanced Deep Learning for Computer Vision / Robotics
  • Probabilistic Graphical Models in Computer Vision
  • etc.

Participants should be able to take initiatives to plan and maintain a continuous workflow, collaborate with teammates and communicate with tutors efficiently.

As many projects consider theoretical aspects of learning theory, a solid basis as well as interest for mathematics is highly recommended.

Prior experiences with machine learning projects are also a strong plus.

Note: it is crucial for interested applicants to also send us an e-mail (bdluam-ss20@vision.in.tum.de) demonstrating their interest and fulfillment of prerequisites. The details will be explained during the pre-course meeting.

Places will be assigned through the TUM matching system (http://matching.in.tum.de).

Course Structure

In the first week there will be a Kick-Off meeting where all projects will be announced to the participants. Each group will consist of about 2 students, and will be supervised by one of the tutors. Interim meetings with the whole group will be scheduled twice during the semester in order to show project progress and exchange ideas. At the end of the semester, each group will present their project with a following Q&A session. There will be no additional written or oral exam. Both the theoretical and practical part of the project will be considered in the final grading.

Course Schedule

Until further notice this course will take place online. As soon as the current situation improves we will notify you.

There will be a preliminary meeting:

There will be the following meetings:

  • Kick-Off: April 22nd - Wednesday at 1-3pm
  • 1st progress meeting: May 27th - Wednesday at 1-3pm
  • 2nd progress meeting: June 24th - Wednesday at 1-3pm
  • Final presentations: July 22nd - Wednesday at 1-4pm
  • Deep Learning, Goodfellow, Bengio, Courville, 2016, http://www.deeplearningbook.org/
  • Machine learning: a probabilistic perspective, Murphy, 2012
  • The Elements of Statistical Learning, Hastie, Tibshirani, Friedman 2001
  • Relevant papers will be announced during the course.

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group



Bernt Schiele (Max Planck Institute for Informatics) will give a talk in the TUM AI lecture series on June 10th, 3pm! Livestream

French-German Machine Learning Symposium

French-German Machine Learning Symposium

The French-German Machine Learning Symposium aims to strengthen interactions and inspire collaborations between both countries. We invited some of the leading ML researchers from France and Germany to this two-day symposium to give a glimpse into their research, and engage in discussions on the future of machine learning and how to strengthen research collaborations in ML between France and Germany.

The list of speakers includes Yann LeCun, Cordelia Schmid, Jean-Bernard Lasserre, Bernhard Schölkopf, and many more! For the full program please visit the webpage.


Ron Kimmel (Technion - Israel Institute of Technology) will give a talk in the TUM AI lecture series on May 6th, 3pm! Livestream


4Seasons Dataset: We have released a novel dataset for benchmarking multi-weather SLAM in autonomous driving.


Hao Li (Pinscreen) will give a talk in the TUM AI lecture series on April 22nd, 8pm! Livestream