Next academic year there will be two new courses within the Master AI: Deep Learning, taught by Efstratios Gavves and Max Welling, and Probabilistic Robotics, taught by Arnoud Visser.
The course on Deep Learning concerns modern, multi-layered neural networks trained on big data. The course will have a particular focus on computer vision and language modelling, which are perhaps the most recognisable and impressive applications of the deep learning theory. The course will consist of a theoretical and a practical part.
In the theoretical part students will be taught the fundamentals of deep learning and the latest, state-of-the-art models that empower popular applications, such as Google Photos, Google Translate, Google Text-to-Speech, Google Brain, Facebook Friend Finder and Self-driving cars. Experts from the field will present their views on different subjects during the theory sessions. Topics include: Back propagation and optimisation, Convolutional neural networks, Recurrent neural networks (RNN), Transfer learning, Restricted Boltzmann Machines and Autoencoders.
During the practical part students will implement from scratch the core versions of some of the aforementioned applications from scratch. The course will focus on state-of-the-art programming frameworks. Students will learn what are the most relevant and frequent practical problems, and how they can be addressed in practice. During the projects, the students will be able to build real-life, interesting and perhaps even marketable applications. Depending on the student’s motivation, the applications can lead to demos that could be publicly presented.
Probabilistic Robotics is a subfield of robotics concerned with the perception and control part. It relies on statistical techniques for representing information and making decisions. By doing so, it accommodates the uncertainty that arises in most contemporary robotics applications. This course is based on the book 'Probabilistic Robotics', by Sebastian Thrun, Wolfram Burgard and Dieter Fox. The book concentrates on the algorithms, and only offers a limited number of exercises. Their suggestion is to accompany the book with a number of practical, hands-on assignments for each chapter. The assignments of this course are designed to understand the basic problems concerning mobile robotics.