Direkt zum Inhalt springen
Computer Vision Group
TUM School of Computation, Information and Technology
Technical University of Munich

Technical University of Munich

Menu

Links

Informatik IX
Computer Vision Group

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

Follow us on:

News

04.03.2024

We have twelve papers accepted to CVPR 2024. Check our publication page for more details.

18.07.2023

We have four papers accepted to ICCV 2023. Check out our publication page for more details.

02.03.2023

CVPR 2023

We have six papers accepted to CVPR 2023. Check out our publication page for more details.

15.10.2022

NeurIPS 2022

We have two papers accepted to NeurIPS 2022. Check out our publication page for more details.

15.10.2022

WACV 2023

We have two papers accepted at WACV 2023. Check out our publication page for more details.

More


Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
teaching:ws2019:dlpractice_ws2019 [2019/07/14 12:09]
Dr. Vladimir Golkov
teaching:ws2019:dlpractice_ws2019 [2020/01/21 22:51]
Dr. Vladimir Golkov
Line 5: Line 5:
  
 ** Winter Semester 2019/2020, TU München ** ** Winter Semester 2019/2020, TU München **
 +
 +<html>
 +<font color="red" size="4"><b>
 +This is the winter semester 2019/2020 course. For the summer semester 2020 course, see
 +</html>
 +[[teaching:ss2020:dlpractice_ss2020|here]].
 +<html>
 +<!-- (Slightly changed course title.)-->
 +</b></font>
 +</html>
 +
 +
 +**Please send applications (including learning goals, programming skills description, code, grade transcripts - see preliminary meeting slides) to dlpractice[at]vision.in.tum.de**\\
  
 **Organizers**:  **Organizers**: 
Line 11: Line 24:
  
 The preliminary meeting (**not** obligatory) takes place on **Monday, 8 July 2019 at 4pm** in [[https://portal.mytum.de/displayRoomMap?roomid=00.06.011@5606|MI Hörsaal 3 (room 00.06.011)]]. The preliminary meeting (**not** obligatory) takes place on **Monday, 8 July 2019 at 4pm** in [[https://portal.mytum.de/displayRoomMap?roomid=00.06.011@5606|MI Hörsaal 3 (room 00.06.011)]].
-Slides from the preliminary meeting (with minor updates) can be downloaded {{:teaching:ws2019:dlpractice_ws2019:dlpremeeting.pdf|here}}.+Slides from the preliminary meeting from the summer semester (similar to winter semester, but note the different dates) can be downloaded {{:teaching:ss2019:dlpractice_ss2019:dlpremeeting.pdf|here}}. 
 + 
 + 
 +<html><!--Registration through the [[https://matching.in.tum.de/|TUM Matching system]] is done <font color="red" size="3"><b>from 19 until 24 July 2019</b></font></html>. Details can be found [[http://docmatching.in.tum.de/index.php/schedule|here]] and [[http://docmatching.in.tum.de/index.php/manual-students|here]]. <html><font color="red" size="3"><b>Sending us an email with sufficient info about yourself ideally several days before you use the Matching website and at the latest until 27 July is crucial for matching success.--> 
 +</b></font></html> 
 +<html><font color="red" size="3"><b>Students who did not register or did not get matched can contact us directly.</b></font></html>
  
-<html><font color="red" size="3"><b>Application: See below</b></font></html> 
  
  
 == Course Description == == Course Description ==
-This course is targeted at excellent students who are on their path to being experts and making key contributions to the progress of science and technology. In this course, we will develop deep learning methods for general and specific applications in computer visionbiomedicine, and related fields. The main purpose of this course is to gain advanced practical experience and profound insights, and to learn when, why and how to apply deep learning to concrete, relevant problems. This is not limited to existing methodsbut on the contrary is about the development of novel methods and solutions. Topics to choose from include the design of advanced architectures and loss functions, tasks beyond supervised learning, advanced data structuresconnections to advanced non-deep/non-learning methods, etc. Experienced supervisors will guide the students and share valuable insights. Students must communicate with the supervisors.+In this course, we will develop deep learning algorithms for concrete applications in the field of computer vision and biomedicine. The main purpose of this course is to gain practical experience with deep learning, and to learn **when, why and how to apply it to concrete, relevant problems**. 
 +The topics will include: 
 +  * Machine learningneural networks, deep learning 
 +  * Standard and advanced network architectures 
 +  * Tasks beyond supervised learning 
 +  * Design of architectureschoice of loss functionstuning of hyperparameters.
  
-The projects will be geared towards developing novel solutions for <html><font color="blue"><b>real open problems</b></font></html> and contributing to scientific publications. Projects with various interesting problems and data representations will be offered.+The projects will be geared towards developing novel solutions for <html><font color="blue"><b>real open problems</b></font></html>. Projects with various interesting problems and data representations will be offered.
  
 **If you want to propose an own project rather than choosing from the projects that we will offer, please discuss with us before 20 July 2019.** **If you want to propose an own project rather than choosing from the projects that we will offer, please discuss with us before 20 July 2019.**
Line 25: Line 47:
  
 == Prerequisites == == Prerequisites ==
-  * Excellent programming skills +Good programming skillsEagerness to acquire and deepen knowledge about how to solve complex problems with machine learning. Passion for mathematics. The course will be focused on practical projects, thus previous knowledge of Python and array programming in NumPy (or in Matlab or similar) is desired. Having also good soft skills (or the willingness to acquire them quickly) and using them is a prerequisite.
-  * Eagerness to acquire and deepen knowledge about how to solve complex problems with machine learning +
-  * Solid skills in mathematics +
-  * Good literature-reading/skimming skills (Theory and practice go hand in hand!) +
-  * Solid knowledge of deep learning theory +
-  * Python and array programming in NumPy (or Matlab or similar) +
-  * PyTorch (or TensorFlow or similar) +
-  * Small gaps in the skills above are OK, because having all other skills means that gaps can be filled quickly +
-  * Good soft skills (or the willingness to acquire them quickly)+
  
-Choice among many different projects will be offeredSome projects will be about biomedicine. Prior knowledge of biomedicine is NOT required.+Knowledge of deep learning and computer vision is recommended/requiredKnowledge of biomedicine is NOT required and can be acquired during this practical course. However, the requirements listed above (e.g. good programming skills, soft skills) are mandatory.
  
-Important soft skills include communication skills, the ability to identify what is unclear, to figure out what questions need to be asked to clarify it, to formulate the questions clearly, and to ask the supervisor without hesitation. Communicating well and strategically is an important rule of the practical course. Almost all difficulties experienced by students are due to not following these rules.+Important soft skills include communication skills, the ability to identify what is unclear, to figure out what questions need to be asked to clarify it, to formulate the questions clearly, and to ask the tutor without hesitation. Communicating well and strategically is an important rule of the practical course. Almost all difficulties experienced by students are due to not following these rules.
  
  
-== Application ==+== Course Structure == 
 +In the first three weeks, there will be lectures every week, focusing on theoretical and practical concepts related to deep learning. During the semester, the students will work in groups on practical deep learning projects. Each group will consist of about 1-2 students, and will be supervised by one of the tutors. 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. The course schedule is detailed below.
  
-Step 1: Send an email to dlpractice[at]vision.in.tum.de <html><font color="red" size="3"><b>ideally several days before you use the Matching website and at the latest when you use it</b></font></html> and include the following: 
-  * Your interests, learning goals 
-  * Description of your skills (see prerequisites) 
-  * Some code you wrote in any context 
-  * All grade transcripts 
-  * Ongoing courses 
- 
-<html><font color="red" size="3"><b>Sending us an email with sufficient info about yourself is crucial for matching success. 
-</b></font></html> 
- 
- 
-Step 2: Apply through the [[https://matching.in.tum.de/|TUM Matching system]] <html><font color="red" size="3"><b>between 19 and 24 July 2019</b></font></html>. Details can be found [[http://docmatching.in.tum.de/index.php/schedule|here]] and [[http://docmatching.in.tum.de/index.php/manual-students|here]]. 
- 
-Students who did not register or did not get matched can contact us at dlpractice[at]vision.in.tum.de 
- 
- 
-== Course Structure == 
-In the first three weeks, there will be lectures every week, focusing on theoretical and practical concepts related to deep learning. During the semester, the students will work in groups and individually on practical deep learning projects. 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 == == Course Schedule ==
Line 69: Line 66:
 22 October: Recap; Network Architecture Design; Understanding and Visualizing; Q&A about Deep Learning\\ 22 October: Recap; Network Architecture Design; Understanding and Visualizing; Q&A about Deep Learning\\
 29 October: Recap; Programming; Evaluating; Q&A about Deep Learning\\ 29 October: Recap; Programming; Evaluating; Q&A about Deep Learning\\
-05 November: Q&A about Deep Learning\\ 
  
 //Note: ECTS credits are the measure of workload. So-called semester weekly hours (Semesterwochenstunden, SWS) are NOT a measure of project work time, but merely of classroom time.//  //Note: ECTS credits are the measure of workload. So-called semester weekly hours (Semesterwochenstunden, SWS) are NOT a measure of project work time, but merely of classroom time.// 

Rechte Seite

Informatik IX
Computer Vision Group

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

Follow us on:

News

04.03.2024

We have twelve papers accepted to CVPR 2024. Check our publication page for more details.

18.07.2023

We have four papers accepted to ICCV 2023. Check out our publication page for more details.

02.03.2023

CVPR 2023

We have six papers accepted to CVPR 2023. Check out our publication page for more details.

15.10.2022

NeurIPS 2022

We have two papers accepted to NeurIPS 2022. Check out our publication page for more details.

15.10.2022

WACV 2023

We have two papers accepted at WACV 2023. Check out our publication page for more details.

More