Dr Michael Kopp is a mathematical modelling specialist bringing decades of expertise in risk assessment and advanced data analysis.
He is also data scientist at Here Technologies in Zurich.
He has been instrumental in bringing about the Traffic4cast competition that builds on billions of real-world data-points to improve short-term traffic forecasting and advance our ability to capture the implicit rules underlying a complex system.
Publications
2020
T. Adler, J. Brandstetter, M. Widrich, A. Mayr, D. Kreil, M. Kopp, G. Klambauer, and S. Hochreiter (2020) Cross-Domain Few-Shot Learning by Representation Fusion. arXiv:2010.06498, 2020-10-13. (more) (download)
D. P. Kreil, M. K. Kopp, D. Jonietz, M. Neun, A. Gruca, P. Herruzo, H. Martin, A. Soleymani, and S. Hochreiter (2020) The surprising efficiency of framing geo-spatial time series forecasting as a video prediction task – Insights from the IARAI Traffic4cast Competition at NeurIPS 2019. Proceedings of the NeurIPS 2019 Competition and Demonstration Track, PMLR 123:232-241, 2020-08-19. (more) (download)
2019
D. Jonietz & M. Kopp (2019) Towards Modeling Geographical Processes with Generative Adversarial Networks (GANs). Proceedings of the 14th International Conference on Spatial Information Theory, COSIT 2019, Regensburg, Germany, Leibniz International Proceedings in Informatics (LIPIcs), 142: 27:1–27:9. (more) (download)
Conferences
Full-day Traffic4cast Symposium
Everyone is welcome to attend the full-day IARAI Traffic4cast Symposion 15 Dec Sunday at the Fairmont Vancouver hotel. Symposium Registration is now open until Saturday 14 Dec 17h, or earlier as soon as...
Traffic4cast Competition Track at NeurIPS 2019
Every NeurIPS delegate is welcome to attend the Traffic4cast Competition Track session on 14 Dec Saturday from 3pm! The session is introduced by our very own Sepp Hochreiter and Leonid Sigal of the University...
Seminars
Patenting AI: why, what and how?
Dr. Alexander Korenberg “specialises in implementing truly transformative patent strategies across a range of fields, from artificial intelligence to cloud services” (IAM 1000, 2019)” and has been called a...
Machine Learning for Location Based Services
Prof. Dr. Ioannis Giannopoulos is a Full Professor for Geoinformation at Vienna University of Technology (TU Wien). Before coming to Vienna, Ioannis was a Postdoctoral Researcher and Lecturer at...
Large Associative Memory Problem in Neurobiology and Machine Learning
Dmitry Krotov, PhD, is a research staff member at the MIT-IBM Watson AI Lab and IBM Research Center in Cambridge, MA. He received his PhD in Physics from Princeton...
Machine Learning in Remote Sensing and Climate Research
Prof. Dr. Wouter Dorigo is head of the research group Climate and Environmental Remote Sensing at TU Wien GEO. His main research interest is remote sensing of soil moisture...
Graph Based Machine Learning Methods for Human Mobility Analysis
Henry Martin is a PhD Student in Geoinformatics at the Chair of Geoinformation Engineering at ETH Zurich and at the Institute of Advanced Research in Artificial Intelligence (IARAI). Since...
Traffic4cast at NeurIPS 2019
Traffic4cast is an interdisciplinary competition on traffic prediction using machine learning, hosted by IARAI. Traffic4cast 2019 dataset includes industrial-scale real-world traffic data with over 100 billion points, provided by HERE Technologies. The...