Laboratory, Deep Learning

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, we want to teach students the practical knowledge that is needed to do research with deep learning and reinforcement learning. 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: Monday, 14.00-16.00 Room: Kinohörsaal/computer pools, Building 082 Beginning: Monday, October 16, 2017 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. Some knowledge about reinforcement learning would be beneficial. Presentations: Lecture 1: Introduction Lecture 2: CNNs CS231 lecture 5 Quick Tensorflow intro Lecture 3: Reinforcement Learning Intro Master Projects/Theses Topics Assignments: You can find the assignments on github Remarks: The short lectures will be in English. The course is open to both Bachelor students and Master students. Further Materal: Get started with Tensorflow A great recent course by Andrej Karpathy on convolutional neural networks A great reinforcement learning course by David Silver Deep learning book by Yoshua Bengio, Ian Goodfellow and Aaron Courville, Deep learning course by Nando de Freitas,