Lecture "Advanced Deep Learning for Robotics"

Lecturer: Berthold Bäuml, Darius Burschka

Contact: berthold.baeuml (at) dlr.de

Modul:IN2349

Type: Lecture

Semester: SS 2018

ECTS: 3.0

                                                                            


Content

 

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.

• Introduction/Motivation

• Introduction to Machine Learning: A Bayesian View

• Advanced Network Architectures

• Generalization & Robustness: Adversarial Training

• Bayesian Deep Learning

• Transfer & Semi-Supervised Learning

• Learning Generative Models: GANs & Autoencoder

• Reinforcement Learning I

• Reinforcement Learning II

• Reinforcement Learning III

• Selected Robotic Applications

  

Material

• I. Goodfellow, Y. Bengio and A. Courville. Deep Learning. MIT Press, 2016.

• Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006.

• Kevin Murphy. “Machine Learning: A Probabilistic Perspective”, MIT Press 2012