This section presents a collection of scientific papers to which I have contributed, or that were inspired by my research and ideas. My keen interest in the foundational principles of deep learning and neural networks has led me to explore a wide array of topics, ranging from in-depth analyses of their inner mechanisms to practical applications in various domains. Many of these endeavors were directly influenced by the projects I participated in. Alongside my colleagues, driven by curiosity and enthusiasm, we ventured into the exploration of somewhat unconventional concepts. I invite you to explore these works and share in our journey of discovery. 🤗

Scholar arXiv R-Gate ORCiD LMU Semantic


  1. Kölle, M., Illium, S., Zorn, M., Nüßlein, J., Suchostawski, P., and Linnhoff-Popien, C. 2023. Improving Primate Sounds Classification using Binary Presorting for Deep Learning. Springer CCIS Series.
  2. Zorn, M., Illium, S., Phan, T., Kaiser, T.K., Linnhoff-Popien, C., and Gabor, T. 2023. Social Neural Network Soups with Surprise Minimization. MIT Press Direct.
  3. Kölle, M., Illium, S., Hahn, C., Schauer, L., Hutter, J., and Linnhoff-Popien, C. 2023. Compression of GPS Trajectories using Autoencoders. arXiv preprint arXiv:2301.07420.


  1. Gabor, T., Illium, S., Zorn, M., et al. 2022. Self-replication in neural networks. Artificial Life 28, 2, 205–223.
  2. Friedrich, M., Illium, S., Fayolle, P.-A., and Linnhoff-Popien, C. 2022. CSG Tree Extraction from 3D Point Clouds and Meshes Using a Hybrid Approach. Computer Vision, Imaging and Computer Graphics Theory and Applications: 15th International Joint Conference, VISIGRAPP 2020 Valletta, Malta, February 27–29, 2020, Revised Selected Papers, Springer International Publishing Cham, 53–79.
  3. Illium, S., Schillman, T., Müller, R., Gabor, T., and Linnhoff-Popien, C. 2022. Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks. 14th International Conference on Agents and Artificial Intelligence: ICAART, 308–315.
  4. Müller, R., Illium, S., Phan, T., Haider, T., and Linnhoff-Popien, C. 2022. Towards Anomaly Detection in Reinforcement Learning. Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, 1799–1803.
  5. Nüßlein, J., Illium, S., Müller, R., Gabor, T., and Linnhoff-Popien, C. 2022. Case-Based Inverse Reinforcement Learning Using Temporal Coherence. Case-Based Reasoning Research and Development: 30th International Conference, ICCBR 2022, Nancy, France, September 12–15, 2022, Proceedings, Springer International Publishing Cham, 304–317.
  6. Illium, S., Zorn, M., Kölle, M., Linnhoff-Popien, C., and Gabor, T. 2022. Constructing Organism Networks from Collaborative Self-Replicators. arXiv preprint arXiv:2212.10078.
  7. Illium, S., Griffin, G., Kölle, M., Zorn, M., Nüßlein, J., and Linnhoff-Popien, C. 2022. VoronoiPatches: Evaluating A New Data Augmentation Method. arXiv preprint arXiv:2212.10054.


  1. Gabor, T., Illium, S., Zorn, M., and Linnhoff-Popien, C. 2021. Goals for self-replicating neural networks. Artificial Life Conference Proceedings 33, MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info …, 101.
  2. Illium, S., Müller, R., Sedlmeier, A., and Popien, C.-L. 2021. Visual Transformers for Primates Classification and Covid Detection. Proc. Interspeech 2021, 451–455.
  3. Müller, R., Illium, S., and Linnhoff-Popien, C. 2021. A Deep and Recurrent Architecture for Primate Vocalization Classification. Proc. Interspeech 2021, 461–465.
  4. Müller, R., Illium, S., and Linnhoff-Popien, C. 2021. Deep recurrent interpolation networks for anomalous sound detection. 2021 International Joint Conference on Neural Networks (IJCNN), IEEE, 1–7.


  1. Müller, R., Langer, S., Ritz, F., Roch, C., Illium, S., and Linnhoff-Popien, C. 2020. Soccer Team Vectors. Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Würzburg, Germany, September 16–20, 2019, Proceedings, Part II, Springer International Publishing, 247–257.
  2. Friedrich, M., Illium, S., Fayolle, P.-A., and Linnhoff-Popien, C. 2020. A Hybrid Approach for Segmenting and Fitting Solid Primitives to 3D Point Clouds. 15th International Joint Conference on Computer Graphics Theory and Applications.
  3. Sedlmeier, A., Müller, R., Illium, S., and Linnhoff-Popien, C. 2020. Policy entropy for out-of-distribution classification. Artificial Neural Networks and Machine Learning–ICANN 2020: 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II 29, Springer International Publishing, 420–431.
  4. Müller, R., Ritz, F., Illium, S., and Linnhoff-Popien, C. 2020. Acoustic anomaly detection for machine sounds based on image transfer learning. arXiv preprint arXiv:2006.03429.
  5. Illium, S., Friese, P.A., Müller, R., and Feld, S. 2020. What to do in the meantime: A service coverage analysis for parked autonomous vehicles. AGILE: GIScience Series 1, 7.
  6. Illium, S., Müller, R., Sedlmeier, A., and Linnhoff-Popien, C. 2020. Surgical mask detection with convolutional neural networks and data augmentations on spectrograms. arXiv preprint arXiv:2008.04590.
  7. Müller, R., Illium, S., Ritz, F., and Schmid, K. 2020. Analysis of feature representations for anomalous sound detection. arXiv preprint arXiv:2012.06282.
  8. Müller, R., Illium, S., Ritz, F., et al. 2020. Acoustic leak detection in water networks. arXiv preprint arXiv:2012.06280.


  1. Gabor, T., Illium, S., Mattausch, A., Belzner, L., and Linnhoff-Popien, C. 2019. Self-Replication in Neural Networks. .
  2. Elsner, D., Langer, S., Ritz, F., Mueller, R., and Illium, S. 2019. Deep neural baselines for computational paralinguistics. arXiv preprint arXiv:1907.02864.


  1. Feld, S., Illium, S., Sedlmeier, A., and Belzner, L. 2018. Trajectory annotation using sequences of spatial perception. Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 329–338.