Course details


Deep learning for computer vision

SS 2020 Ulf Krumnack, Axel Schaffland
B.Sc modules:
CS-BWP-AI - Artificial Intelligence
CS-BWP-NI - Neuroinformatics
KOGW-WPM-KI - Artificial Intelligence
KOGW-WPM-NI - Neuroinformatics
M.Sc modules:
CC-MP-IDC - Interdisciplinary Course
CC-MWP-AI - Artificial Intelligence
CC-MWP-NI - Neuroinformatics
CS-MP-IDC - Interdisciplinary Course
CS-MWP-AI - Artificial Intelligence
CS-MWP-NI - Neuroinformatics
KOGW-MPM-IDK - Interdisciplinary courses
KOGW-MWPM-KI - Major subject Artificial Intelligence
KOGW-MWPM-NIR - Major subject Neuroinformatics and Robotics

Bachelor elective course
Master elective course
Doctorate program
Fri: 10-12

In recent years, deep neural networks have shown tremendous success in almost all fields of computer vision, outperforming most alternative techniques. Yet many aspects of this paradigm are not well understood, and recent findings hint to systematic problems in this branch of machine learning. In this seminar, we will study different approaches to analyze and understand the operation of deep networks with the goal of identifying theoretical and practical challenges. On the practical side will focus on the application of deep learning to the problems of computer vision and especially imageregistration and discuss different proposals to address these tasks. This course targets at master and advanced bachelor students. The ideal participant will have some background in machine learning, computer vision, and deep learning (e.g. on the level of the "Implementing ANNs with TensorFlow").