This lecture covers Deep Learning for automatic image analysis, e.g. for classifying images into categories or detecting and distinguishing persons. Deep Learning has recently lead to breakthroughs in these fields; in certain problems, the performance of current methods based on this technology is similar or even better than that of humans - a novelty in this field. The goal of this lecture is to provide a comprehensive introduction to Deep Learning and its application for solving practical problems.
Deep learning for automatic image analysis:
* Brief recap of Computer Vision and Image Processing* Machine Learning: overview, parametric models, iterative optimization* Feedforward Neural Networks, backpropagation* Convolutional Neural Networks for classification, detection, and segmentation* Software libraries and practical aspects* Preprocessing, data augmentation, regularization, visualizations* Guest lectures on medical applications and ethical aspects
The contents presented in the lecture will be applied in exercises.
ECTS breakdown: 3 ECTS = 75h
16h lecture34h programming exercises24h exam preparations1h exam---75h
Written exam (50%) and compulsory programming exercises (50%).
The student has to be enrolled for at least one of the studies listed below
