Module Handbook

  • Dynamischer Default-Fachbereich geändert auf INF

Module INF-73-84-M-7

Very Deep Learning for Computer Vision (Projekt) (M, 8.0 LP)

Module Identification

Module Number Module Name CP (Effort)
INF-73-84-M-7 Very Deep Learning for Computer Vision (Projekt) 8.0 CP (240 h)

Basedata

CP, Effort 8.0 CP = 240 h
Position of the semester 1 Sem. irreg.
Level [7] Master (Advanced)
Language [EN] English
Module Manager
Lecturers
Area of study [INF-KI] Intelligent Systems
Reference course of study [INF-88.79-SG] M.Sc. Computer Science
Livecycle-State [NORM] Active

Courses

Type/SWS Course Number Title Choice in
Module-Part
Presence-Time /
Self-Study
SL SL is
required for exa.
PL CP Sem.
4L INF-73-84-K-7
Very Deep Learning for Computer Vision (Projekt)
P 56 h 184 h
PRAES
- PL1 8.0 irreg.
  • About [INF-73-84-K-7]: Title: "Very Deep Learning for Computer Vision (Projekt)"; Presence-Time: 56 h; Self-Study: 184 h
  • About [INF-73-84-K-7]: The study achievement "[PRAES] presentation" must be obtained.

Evaluation of grades

The module is not graded (only study achievements)..


Contents

  • Advanced Convolutional Networks
  • Bleeding-Edge Architectures (depending on the most recent publications in Deep Learning)
  • Customized methods for specific applications (depending on the chosen task to work on)

Competencies / intended learning achievements

After successfully completing the module, students will be able to
  • Possibly working in a team to solve a problem
  • Get a deep understanding of one difficult task in computer vision and pattern recognition
  • Find failure cases of existing deep learning methods
  • Understand and implement advanced deep learning methods
  • Presentation of the developed algorithm

Requirements for attendance of the module (informal)

None

Requirements for attendance of the module (formal)

None

References to Module / Module Number [INF-73-84-M-7]

Course of Study Section Choice/Obligation
[INF-88.79-SG] M.Sc. Computer Science [Specialisation] Specialization 1 [WP] Compulsory Elective