Adrian Šošić

Adrian Šošić

Member of the Signal Processing Group at the Institute of Telecommunications, TU Darmstadt.

Merckstraße 25
64283 Darmstadt

Office: S3|06 250

+49 6151 16-21348
+49 6151 16-21342


go to list

Office Hours: Mondays, 15:30-18:30

Adrian Šošić received his B.Sc. and M.Sc. degrees in Electrical Engineering and Information Technology from Technische Universität Darmstadt in October 2010 and May 2013, respectively. During his studies, he spent time at University College Cork (UCC), Ireland. In his master thesis “Markov Assumptions for Non-negative Matrix Factorization” he investigated how fundamental concepts of linear dynamical systems and non-negative representations can be combined in order to learn parts-based models for sequential data. The representations developed in his thesis can be applied, for instance, in sequence classification, e.g. human action recognition from video data.

In September 2013, Adrian joined the Signal Processing Group at TU Darmstadt and commenced working on his Ph.D.

Research

Adrian's research interests center around topics from modern machine learning, statistical signal processing, image processing, decision-making, reinforcement learning, and game theory. He is especially interested in the methodology of Bayesian inference and his goal is to develop robust inference methods that allow to deal with uncertainty in a principled manner.

Currently he is working on inference methods in (large-scale) multi-agent settings as they appear in many biological systems, e.g. in animal swarms.

Adrian is collaborating with the Bioinspired Communication Systems Lab under the supervision of Prof. Dr. Heinz Koeppl and Prof. Gerhard Neumann from Lincoln Centre for Autonomous Systems Research.

Completed Student Projects

Rong Zhi Deep Reinforcement Learning under Uncertainty for Autonomous Driving Master Thesis ongoing
Mahmood Omaira Deep Neural Networks for Radar-Based Human Gait Recognition Master Thesis 12/2017
Burak Celik
Bayesian Nonparametric Clustering ATISSP Seminar 07/2017
Benjamin Graf
Learning a Communication Scheme in Homogeneous Multi-Agent Systems Master Thesis 05/2017
Sanket Pratap Shinde
(Master Thesis)
Partially Observable Markov Decision Processes for Continuous States and Observations for Robotics Master Thesis 04/2017
Mengyao Zhang
A Change Detection Approach in Map-Building for Autonomous Vehicles Master Thesis 02/2017
Maximilian Hüttenrauch
Guided Deep Reinforcement
Learning for Robot Swarms
Master Thesis 08/2016
Frederik Bous & Edin Ragibović
Localisation with the Particle Filter ATISSP Seminar 07/2016
Mahmoud El-Hindi
Reinforcement Learning Proseminar 05/2016
Romain Gemble
Investigation and Implementation of Algorithms for Music Source Separation Bachelor Thesis 02/2016
Sandro Kecanovic
Bayesian Non-negative Matrix Factorization Bachelor Thesis 12/2015
Sandro Kecanovic
Non-negative Matrix Factorization techniques Project Seminar 08/2015
Benjamin Graf,
Rosa Maria Carpio López
& Daniel Scheuermann

Reinforcement Learning for Black Jack ATISSP Seminar 07/2015
Zhengqi Qian
Reinforcement Learning in Swarm Systems Master Thesis 07/2015
Mateesh Bhave
Learning Class Uncertainties using Neural Networks Master Thesis 02/2015
Sandro Kecanovic
Machine Learning: An Overview Proseminar 12/2014
Jun Liu & Mengyao Zhang
Reinforcement Learning ATISSP Seminar 07/2014

Teaching

WS 13/14
  • Digital Signal Processing Lab
SS 14
  • Digital Signal Processing Lab
  • Advances in Digital Signal Processing: Imaging and Image Processing
  • Advanced Topics in Statistical Signal Processing
WS 14/15
  • Digital Signal Processing Lab
SS 15
  • Digital Signal Processing Lab
  • Advances in Digital Signal Processing: Imaging and Image Processing
  • Advanced Topics in Statistical Signal Processing
SS 16
  • Advances in Digital Signal Processing: Imaging and Image Processing
  • Advanced Topics in Statistical Signal Processing
SS 17
  • Advances in Digital Signal Processing: Imaging and Image Processing
  • Advanced Topics in Statistical Signal Processing
WS 17/18
  • Machine Learning in Information and Communication Technology
SS 18
  • Advances in Digital Signal Processing: Imaging and Image Processing
  • Advanced Topics in Statistical Signal Processing
  

Publications

Group by: Date | Item type | No grouping
Jump to: 2018 | 2017 | 2016 | 2014 | 2012
Number of items: 13.

2018

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. :
A Bayesian Approach to Policy Recognition and State Representation Learning.
[Online-Edition: https://doi.org/10.1109/TPAMI.2017.2711024]
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 40 (6) pp. 1295-1308.
[Article], (2018)

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. :
Reinforcement Learning in a Continuum of Agents.
[Online-Edition: http://rdcu.be/wKay]
In: Swarm Intelligence, 12 (1) pp. 23-51.
[Article], (2018)

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. :
Inverse Reinforcement Learning via Nonparametric Subgoal Modeling.
[Online-Edition: https://aaai.org/ocs/index.php/SSS/SSS18/paper/view/17531/15...]
In: AAAI Spring Symposium on Data-Efficient Reinforcement Learning .
[Conference or workshop item], (2018)

Šošić, A. ; Rueckert, E. ; Peters, J. ; Zoubir, A. M. ; Koeppl, H. :
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling.
[Online-Edition: http://arxiv.org/abs/1803.00444]
In: Journal of Machine Learning Research (accepted)
[Article], (2018)

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. :
Local communication protocols for learning complex swarm behaviors with deep reinforcement learning.
In: International Conference on Swarm Intelligence .
[Conference or workshop item], (2018)

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. :
Guided Deep Reinforcement Learning for Swarm Systems.
[Online-Edition: https://arxiv.org/abs/1709.06011]
In: Journal of Machine Learning Research (under review)
[Article], (2018)

2017

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. :
Guided Deep Reinforcement Learning for Swarm Systems.
[Online-Edition: https://arxiv.org/abs/1709.06011]
In: AAMAS Workshop on Autonomous Robots and Multirobot Systems.
[Conference or workshop item], (2017)

Šošić, A. ; KhudaBukhsh, W. R. ; Zoubir, A. M. ; Koeppl, H. :
Inverse Reinforcement Learning in Swarm Systems (Best Paper Award Finalist).
[Online-Edition: http://dl.acm.org/citation.cfm?id=3091320]
In: International Conference on Autonomous Agents and Multiagent Systems .
[Conference or workshop item], (2017)

Šošić, A. ; KhudaBukhsh, W. R. ; Zoubir, A. M. ; Koeppl, H. :
Inverse Reinforcement Learning in Swarm Systems.
In: AAMAS Workshop on Transfer in Reinforcement Learning .
[Conference or workshop item], (2017)

2016

Šošić, A. ; Zoubir, A. M. ; Koeppl, H. :
Policy Recognition via Expectation Maximization.
[Online-Edition: https://doi.org/10.1109/icassp.2016.7472589]
In: IEEE International Conference on Acoustics, Speech and Signal Processing.
[Conference or workshop item], (2016)

Hüttenrauch, M. ; Šošić, A. ; Neumann, G. :
Guided Deep Reinforcement Learning for Swarm Systems.
In: NIPS Workshop on Learning, Inference and Control of Multi-Agent Systems.
[Conference or workshop item], (2016)

2014

Guthier, T. ; Šošić, A. ; Willert, V. ; Eggert, J. :
sNN-LDS: Spatio-temporal Non-negative Sparse Coding for Human Action Recognition.
[Online-Edition: http://dx.doi.org/10.1007/978-3-319-11179-7_24]
In: Artificial Neural Networks and Machine Learning – ICANN 2014. Lecture Notes in Computer Science, 8681. Springer International Publishing , pp. 185-192.
[Book section], (2014)

2012

Guthier, T. ; Šošić, A. ; Willert, V. ; Eggert, J. :
Finding a Tradeoff between Compression and Loss in Motion Compensated Video Coding.
In: SIGMAP and WINSYS 2012 - Proceedings of the International Conference on Signal Processing and Multimedia Applications and International Conference on Wireless Information Networks and Systems, Rome, Italy, 24-27 July, 2012, SIGMAP is part of ICETE - The I.
[Conference or workshop item], (2012)

This list was generated on Mon Oct 15 05:00:13 2018 CEST.