0000003678 19S 6SWS PR Practical Course - Hands-on Deep Learning for Computer Vision and Biomedicine (IN0012, IN2106, IN4204)   Hilfe Logo

LV - Detailansicht

Wichtigste Meldungen anzeigenMeldungsfenster schließen
Allgemeine Angaben
Practical Course - Hands-on Deep Learning for Computer Vision and Biomedicine (IN0012, IN2106, IN4204) 
practical training
Summer semester 2019
Informatics 9 - Chair of Computer Vision and Artificial Intelligence (Prof. Cremers)
(Contact information)
Angaben zur Abhaltung

In this course, we will develop and implement 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:

- Basics of machine learning and deep learning
- Standard and advanced architectures
- Tasks beyond supervised learning
- Design of architectures, choice of loss functions, tuning of hyperparameters.

The projects will be geared towards developing novel solutions for REAL OPEN PROBLEMS. Projects with different interesting problems and data representations will be offered.

Good programming skills. Eagerness 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 Matlab or similar) is desired. Having good soft skills (or the willingness to acquire them quickly) and using them is a prerequisite.

Knowledge deep learning and computer vision is recommended/required. Knowledge 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: communication skills, ability to identify what is unclear, formulate questions precisely. Communicating well and strategically is an important rule.

Don't forget to apply by email.
Upon completion of this module, students will have acquired practical experience in solving large-scale problems with deep learning. They will be able to find and assess a novel problem, create and evaluate appropriate data representations, choose appropriate methods, design and improve deep neural network architectures and training procedures, locate and resolve issues, evaluate and present results.

The lectures will be devoted to theoretical and practical concepts related to deep learning. Subsequently, students will work in groups and individually during the semester in order to complete projects consisting of real problems. Regular communication with experienced tutors will ensure that appropriate approaches are used and learning objectives are attained.
Für die Anmeldung zur Teilnahme müssen Sie sich in TUMonline als Studierende/r identifizieren.
Note: PLEASE EMAIL INFO ABOUT YOUR KNOWLEDGE AND INTERESTS TO dlpractice@vision.in.tum.de (deadline is 15 February 2019). SEE PRELIMINARY-MEETING SLIDES AT https://vision.in.tum.de/teaching/ss2019/dlpractice_ss2019 . SENDING AN EMAIL IS CRUCIAL FOR MATCHING SUCCESS.
Places will be assigned through the TUM matching system (http://matching.in.tum.de).
- Materials presented during the three lectures in the beginning of the practical course
- https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html
- http://www.deeplearningbook.org/
- http://neuralnetworksanddeeplearning.com/
- Christopher M. Bishop. “Pattern Recognition and Machine Learning”, Springer, 2006.
Additional information
additional information