[IDV] - [de] - [Deep Vision]


Deep Vision [2021 Sommer]
Code
IDV
Name
Deep Vision
LP
6 LP
Dauer
one semester
Angebotsturnus
irregular
Format
lecture 2 SWS, tutorial 2 SWS
Arbeitsaufwand
180h; thereof
60h lectures and tutorials
70h lecture wrap-up, programming excercises, and homework
50h preparation for project work, examination
Verwendbarkeit
B.Sc. Angewandte Informatik,
M.Sc. Angewandte Informatik,
M.Sc. Scientific Computing
Sprache
Lehrende
Prüfungsschema
Lernziele To have reached an understanding of the foundations underlying deep learning
To be able to practically apply deep learning algorithms to new problems in Computer Vision
To have a firm command of the algorithmic basics and to be able to analyze and solve new problems in novel application areas
To be capable of understanding and analyzing the latest publications in deep learning and Computer Vision and to evaluate their strengths and weaknesses.
To have reached understanding of state-of-the-art deep learning algorithms for Computer Vision with the ability to relate and contrast different concepts.
Lerninhalte Methods in Computer Vision based on Deep Learning, esp.:
• deep learning in Computer Vision and convolutional neural networks
• generative/discriminative methods
• supervised/unsupervised methods, reinforcement learning
• video analysis
• Object and action recognition
• local and global feature extraction
• hierarchical object representations
• novel applications
Teilnahme-
voraus-
setzungen
recommended are: solid programming skills and knowledge of basic calculus, statistics, and linear algebra
Vergabe der LP und Modulendnote Bestehen der Modulprüfung
Nützliche Literatur Will be presented in class