Deep Learning for Computer Vision

Contents:
- Notions, basic techniques, and key problems in machine learning
- Defining and training deep neural network models
- Backpropagation
- Nuts and bolts in training deep neural networks
- Hyperparameter optimization
- Tensorflow
- Convolutional Neural Networks
- Object detection and image segmentation
- Visualizing and understanding deep neural networks
- Recurrent Neural Networks
- Generative Models
- U-Nets and their applications
- Model compression

Examination:
There will be independent projects in the second half of the semester (topics can be proposed by participants) that students will work on in small groups and that will serve as the basis for grading.

Lecturers

Details

Course type
Lectures
Credits
6
Term
Winter Term 2018/2019

Dates

Lecture
Takes place every week on Thursday from 10:00 to 12:00 in room NA 3/99.
First appointment is on 11.10.2018
Last appointment is on 31.01.2019
Exercise
Takes place every week on Monday from 10:00 to 12:00 in room NB 3/57.
First appointment is on 15.10.2018
Last appointment is on 28.01.2019

The Institut für Neuroinformatik (INI) is a central research unit of the Ruhr-Universität Bochum. We aim to understand the fundamental principles through which organisms generate behavior and cognition while linked to their environments through sensory systems and while acting in those environments through effector systems. Inspired by our insights into such natural cognitive systems, we seek new solutions to problems of information processing in artificial cognitive systems. We draw from a variety of disciplines that include experimental approaches from psychology and neurophysiology as well as theoretical approaches from physics, mathematics, electrical engineering and applied computer science.

Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany

Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210