Laboratory, Deep Learning for Robotics

Deep learning has brought a revolution to AI research. A good understanding of the principles of deep networks and experience in training them has become one of the main assets for successful research and development of new technology in machine learning, computer vision, and robotics. In this course, which will be jointly organized by the two machine learning groups, the robotics group, and the computer vision group, we want to teach students the practical knowledge that is needed to do research with deep learning in any of these fields. The course starts with some introductory lectures, continues with first some smaller and then larger projects. You must work in teams of 2-3 persons. There will be a final presentation of your project results at the end of the semester.

Lecture/Exercises: (2 SWS) Friday, 14-16 Room: Kinohörsaal/computer pools, Building 082 Beginning: Friday, October 21, 2016 ECTS Credits: 4 or 6 Requirements: Fundamental programming skills in Python. Basic knowledge about machine learning techniques (supervised learning, classification, regression, logistic regression). Some experience with the Linux toolchain (text editor, compiler, linker, debugger) is recommended. Remarks: The short lectures will be in English. The course is open to both Bachelor students (for their Bachelor project) and Master students (for their lab course). To reflect the larger experience of Master students, they must finish more involved project tasks to pass. The final project also provides 4 and 6 ECTS variants of the Bachelor project. Further Materal: A great recent course by Andrej Karpathy on convolutional neural networks Course on Neural Networks by Hugo Larochelle, Deep learning tutorial by Kyunghyun Cho Stanford course on deep learning and unsupervised feature learning Deep learning book by Yoshua Bengio, Ian Goodfellow and Aaron Courville, Deep learning course by Nando de Freitas,