This website is no longer updated.

As of 1.10.2022, the Faculty of Physics has been merged into the TUM School of Natural Sciences with the website For more information read Conversion of Websites.

de | en

Advanced Deep Learning for Robotics (IN2349)

Course 0000003810 in SS 2018

General Data

Course Type lecture
Semester Weekly Hours 2 SWS
Organisational Unit Informatics 6 - Chair of Robotics, Artificial Intelligence and Real-time Systems (Prof. Knoll)
Lecturers Berthold Bäuml
Responsible/Coordination: Darius Burschka

Assignment to Modules

Further Information

Courses are together with exams the building blocks for modules. Please keep in mind that information on the contents, learning outcomes and, especially examination conditions are given on the module level only – see section "Assignment to Modules" above.

additional remarks The lectures will provide extensive theoretical aspects of neural networks and in particular deep learning architectures, specifically for advanced methods in the field of Robotics, esp. deep reinforcement learning. - Recap of deep learning in neural networks (multilayer perceptrons, CNN, automatic differentiation, optimization and regularization methods) - Self-supervised learning - Deep reinforcement learning (Bellman equation, Deep Q-Learning Deep Deterministic Policy Gradients, Trust Region Policy Optimization) - Advanced deep reinforcement learning (attention mechanisms, Neural Turing Machines, Alpha Go, Alpha Zero, ...) - Transfer and One Shot Learning (Siamese Networks, Progressive Neural Networks, combining simulated and real world samples) - Network architectures guaranteeing robustness and providing confidence values for predictions; analysis of learned models - Robotic applications (learning to grasp; tactile material classification; fast motion planning) - Software frameworks for advanced deep learning (TensorFlow, Keras, Deepmind Sonnett, Facebook Torch) - Open problems in Deep Learning for Robotics
Links Course documents
E-Learning course (e. g. Moodle)
Additional information
TUMonline entry
Top of page