Introduction to Deep Learning for Computer Vision
Limited number of participants! Please enroll yourself by sending an email to sebastian.houben@ini.rub.de stating your name, student id (Matrikelnummer), course of studies and current semester. Enrollment period: from December 1, 2017 to January 12, 2018.
Please do not forget to have you enrolled in this course by your Prüfungsamt as well.
This one-week hands-on lab course is directed at students in their Master's curriculum and covers basic operations of image processing, machine learning techniques, and end-to-end training of deep convolutional neural networks. The course focuses on a practical multi-class image classification problem, the recognition of different traffic signs in natural images. Each day is divided into an introduction to the topic and followed by a period of hands-on exercises, which can be prepared in groups of two or three students.
Lecturers
Details
- Course type
- Lab courses
- Credits
- 2 CP
- Term
- Winter Term 2017/2018
Dates
- Preliminary meeting
- Takes place on 01.02.2018 from 10:15 to 11:15 in room NB 3/57.
- Lab course
-
Takes place
every day from 10:15 to 17:00 in room NA 04/494.
First appointment is on 05.02.2018
Last appointment is on 09.02.2018
Requirements
Interested students should be largely familiar with at least one imperative programming language, preferably Python. Basic knowledge of machine learning and computer vision is beneficial, but not strictly required. The course will be given in English.
Documents
| Lecture slides | Peparatory meeting |
| Lecture slides | Handouts Day 1 |
| Lecture slides | Handouts Day 2 |
| Document | Preparatory Meeting Handouts |
| Lecture slides | Handouts Day 3 |
| Lecture slides | Handouts Day 4 |
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, in particular machine learning, artificial intelligence, and computer vision.
Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany
Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210