Course
DLO - image processing master
PDF Course Catalog Deutsche Version: DLO
Version: 1 | Last Change: 28.10.2019 15:21 | Draft: 0 | Status: vom verantwortlichen Dozent freigegeben
| Long name | image processing master |
|---|---|
| Approving CModule | DLO_MaET, DLO_MaMT, DLO_MaTIN |
| Responsible |
Prof. Dr. Jan Salmen
Professor Fakultät IME |
| Level | Master |
| Semester in the year | summer semester |
| Duration | Semester |
| Hours in self-study | 80 |
| ECTS | 5 |
| Professors |
Prof. Dr. Jan Salmen
Professor Fakultät IME |
| Requirements | The students should have some basic knowledge about image processing and pattern recognition |
| Language | German |
| Separate final exam | Yes |
Literature
I. Goodfellow, Y. Bengio und A. Courville. Deep Learning. MIT Press, 2016
C. C. Aggarwal. Neural Networks and Deep Learning: A Textbook. Springer, 2018
C. Bishop und H. Bishop. Deep Learning: Foundations and Concepts. Springer, 2024
D. V. Godoy. Deep Learning with PyTorch Step-by-Step: A Beginner’s Guide. Fundamentals. 2022
D. V. Godoy. Deep Learning with PyTorch Step-by-Step: A Beginner’s Guide. Computer Vision. 2022
C. C. Aggarwal. Neural Networks and Deep Learning: A Textbook. Springer, 2018
C. Bishop und H. Bishop. Deep Learning: Foundations and Concepts. Springer, 2024
D. V. Godoy. Deep Learning with PyTorch Step-by-Step: A Beginner’s Guide. Fundamentals. 2022
D. V. Godoy. Deep Learning with PyTorch Step-by-Step: A Beginner’s Guide. Computer Vision. 2022
Final exam
Details
project documentationMinimum standard
The documentation has to contain a description of the applied method and the achieved results. Principles of scientific work have to be applied. The used programs must run without errors, and the results must be plausible.Exam Type
project documentationLearning goals
Knowledge
Deep learning algorithms and their application for object recognition in images.
learneing algorithms, their training and evaluation
learneing algorithms, their training and evaluation
Expenditure classroom teaching
| Type | Attendance (h/Wk.) |
|---|---|
| Lecture | 2 |
| Tutorial (voluntary) | 0 |
Special literature
keine/none
Special requirements
keine
Accompanying material
keine/none
Separate exam
none
Learning goals
Skills
training of a neural network
evaluation of the performance of a neural network
evaluation of the performance of a neural network
Expenditure classroom teaching
| Type | Attendance (h/Wk.) |
|---|---|
| Practical training | 3 |
| Tutorial (voluntary) | 0 |
Special literature
keine/none
Special requirements
keine
Accompanying material
keine/none
Separate exam
Exam Type
solving exercises within limited functional / methodical scopeDetails
Training and evaluation of a neural network with dedicated examplesMinimum standard
Presence and active colaboration
Bei Fehlern, bitte Mitteilung an die
Webredaktion der Fakultät IME
Webredaktion der Fakultät IME
© 2022 Technische Hochschule Köln