[DMANET] Postdoctoral Fellowship: Neural Networks and Tropical Geometry – Toulouse

Dear colleagues, We are pleased to announce a postdoctoral fellowship opportunity in the interdisciplinary field of neural networks and tropical geometry, funded through the "Combining Polynomial Optimization and Machine Learning" (POPML4PS) chair of the ANITI AI cluster. Position Overview: The successful candidate will work with Mateusz Skomra (LAAS-CNRS, Toulouse) and Georg Loho (FU Berlin) on research at the intersection of discrete/tropical geometry and machine learning. The project aims to leverage tropical and discrete geometric tools to advance theoretical understanding and practical applications of neural networks, especially those using ReLU activation functions. Key Research Directions (non-exhaustive):     Exploring neural networks as models of computation     Static analysis and robustness certification of ReLU neural networks     Studying geometric objects associated with ReLU networks using tropical geometry Location, duration, and salary: The position is based at LAAS-CNRS in Toulouse, France, within the POP team led by Victor Magron. The contract is for 12 months, with a possible extension for another 12 months. The position offers ample travel funding and the remuneration is according to the candidate profile. Requirements: We seek candidates with a strong background in tropical geometry, mathematical foundations of machine learning, or related areas, and basic programming skills. A PhD in mathematics, computer science, or a related field is required, along with a strong publication record. Application Process: Applications should include a full CV including list of publications, a motivation letter (max. 2 pages), and the names of potential referees. Please send your application to Georg Loho (georg.loho@math.fu-berlin.de) and Mateusz Skomra (mateusz.skomra@laas.fr), with “Postdoc candidate NNTG” in the subject line. Timeline: Applications received by May 31, 2026, will receive full consideration. However, we will continue to accept late applications until the position is filled. We welcome applications from all qualified candidates and encourage underrepresented groups to apply. For further details, please refer to the announcement on the website https://homepages.laas.fr/mskomra/ or contact us directly. Best regards, Georg Loho and Mateusz Skomra ********************************************************** * * Contributions to be spread via DMANET are submitted to * * DMANET@zpr.uni-koeln.de * * Replies to a message carried on DMANET should NOT be * addressed to DMANET but to the original sender. The * original sender, however, is invited to prepare an * update of the replies received and to communicate it * via DMANET. * * DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET) * http://www.zaik.uni-koeln.de/AFS/publications/dmanet/ * **********************************************************