
Univ.-Prof. Dr. Elmar Rueckert is organizing this research seminar. Topics include research in AI, machine and deep learning, robotics, cyber-physical-systems and process informatics.
Language:
English only
Are you an undergraduate, graduate, or doctoral student and want to learn more about AI?
This course will give you the opportunity to listen to research presentations of latest achievements. The target audience are non-experts. Thus no prior knowledge in AI is required.
To get the ECTS credits, you will select a research paper, read it and present it within the research seminar (10-15 min presentation). Instead of selecting a paper of our list, you can also suggest a paper. This suggestion has to be discussed with Univ.-Prof. Dr. Elmar Rueckert first.
After the presentation, the paper is discussed for 10-15 min.
Further, external presenters that are leading researchers in AI will be invited. External speakers will present their research in 30-45 min, followed by a 15 min discussion.
Links and Resources
Location & Time
- Location: HS Thermoprozesstechnik (HS TPT) with some exceptions, see the list of dates below.
- Dates: Thursdays 15:15-17:00, with some exceptions, see here the list of the dates.
List of Talks and Dates
- 06.10.22 15:15 (HS TPT)
- Univ.-Prof. Dr. Elmar Rueckert, Introductory Slides.
- 18.10.22 10:15 (HS TPT)
- M.Sc. thesis: Benjamin Schödinger on A framework for learning Vision and Tactile correlation.
- 20.10.22 15:15 (HS TPT)
- Nikolaus Feith, M.Sc. and doctoral student at CPS presents the paper ‘VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation’ by Hoque et al.
- Fotios Lygerakis, M.Eng. and doctoral student at CPS presents the paper Contrastive Learning as Goal-Conditioned Reinforcement Learning by B. Eysenbach et al.
- 11.11.22 08:15 (HS TPT)
- Vedant Dave, M.Sc. and doctoral student at CPS presents the paper
‘Hamiltonian Generative Networks‘ by Peter Toth et al. - Linus Nwankwo, M.Sc. and doctoral student at CPS presents the paper ‘Socially Aware Motion Planning with Deep Reinforcement Learning’ by Fan Chen et al.
- Vedant Dave, M.Sc. and doctoral student at CPS presents the paper
- 15.11.22 11:00 (CPS Office of Elmar Rueckert)
-
- Stefan Wallner, M.Sc. and doctoral student at MUL presents his doctoral thesis topic on ‘Multi energy systems modelling’
-
- 18.11.22 13:15 (HS TPT)
- Honghu Xue, M.Sc. and doctoral student at Uni Luebeck presents the paper ‘End-To-End Deep Reinforcement Learning for First-person Pedestrian Visual Navigation in Urban Environments‘ by Xue et al.
- 1 Free Slot
- 25.11.22 08:15 (Elmar’s Office) 2 Free Slots
- 01.12.22 15:15 (HS TPT) 2 Free Slots
- 15.12.22 15:15 (HS TPT)
- Sahar Keshavarz, M.Sc. and doctoral student at DPE. She will present the paper ‘Deep Hierarchical Planning from Pixels (preprint)’ by D. Hafner et al.
- 26.01.23 15:15 (HS Umweltschutz)
- Guest Lecturer: Nils Rottmann, Ph.D. on ROS, ROS-mobile, and industrial applications of mobile robotics.
- 02.02.23 15:15 2 Free Slots
Available Research Papers to Select
- Predictive Whittle Networks for Time Series by Yu et al. (UAI 2022)
- Natural Gradient Shared Control by Oh, Wu, Toussaint and Mainprice
- Learning to solve sequential physical
reasoning problems from a scene image by Driess, Ha and Toussaint (IJRR 2021) - Deep Visual Constraints: Neural Implicit Models for Manipulation
Planning from Visual Input by Ha, Driess and Toussaint - AW-Opt: Learning Robotic Skills with Imitation and
Reinforcement at Scale by Lu et al. (CoRL 2021) - Decision Transformer: Reinforcement Learning via Sequence Modeling (NeurIPS 2021) by L. Chen et al
- CURL: Contrastive Unsupervised Representations for Reinforcement Learning (ICML 2020) by A. Srinivas et al
- Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble (CoRL 2021) by S. Lee et al
- Deep Hierarchical Planning from Pixels (preprint) by D. Hafner et al
- Offline Meta-Reinforcement Learning with Online Self-Supervision by Pong et al. (ICML 2022)
- Information is Power: Intrinsic Control via Information Capture by Rhinehart et al. (NeurIPS 2021)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks by Finn et al.
- Event-based Asynchronous Sparse Convolutional Networks by Messikommer et al.
- Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statistics by Wang et al.
- A Spiking Neural Network Model of Depth from Defocus for Event-based Neuromorphic Vision by Haessig et al.
- Dream to Control: Learning Behaviors by Latent Imagination by Hafner et al.