Machine Learning Seminar

The aim of the Machine Learning Seminar series is to harbor presentations of fundamental and methodological advances in data science and machine learning as well as to discuss application areas presented by domain specialists. The uniqueness of the seminar series lies in its attempt to extract common denominators between domain areas and to challenge existing methodologies. The focus is thus on theory and applications to a wide range of domains, including Computational Physics and Engineering, Computational Biology and Life Sciences, Computational Behavioural and Social Sciences.

The seminar is aiming to bring together young and more experienced researchers from various disciplines and to exchange ideas on Machine Learning techniques. The seminar is run under the auspices of the DRIVEN PRIDE project that is funded by the FNR and led by Andreas Zilian, as well as the widening participation DRIVEN project funded by H2020 and coordinated by Stéphane Bordas. It also welcomes talks by researchers from a wider collaborative network, including, but not restricted to, early stage researchers in RAINBOW ITN as well as current and incoming individual Marie Skłodowska Curie fellows. 

The usual format is the following: a short presentation (15-20min) followed  by a longer discussion (30-40min). The usual time is Wednesdays, 10:00 a.m. (CET). 

If you are interested to join, please contact Jakub Lengiewicz.


2023.01.18Philippe BarattaAix-Marseille University and CPPM, Marseille, FranceStatistical methods in observational Cosmologydetails
2023.01.11Haralampos HatzikirouFaculty of Mathematics, Khalifa University, United Arab EmiratesHow can we make tumour predictions when we do not understand everything?details
2022.11.30Andres Posada MorenoRWTH Aachen UniversityConcept-based explanations for convolutional neural networksdetails
2022.11.23David Wagg University of SheffieldA time-evolving digital twin tool for engineering dynamics applicationsdetails
2022.11.09Orhan ErmisLuxembourg Institute of Science and Technology A CNN-based Semi-Supervised Learning Approach for the Detection of SS7 Attacksdetails
2022.10.26Oscar CastroLuxembourg Institute of Science and TechnologyMulti-target Compiler for the Deployment of Machine Learning Modelsdetails
2022.10.05Inès ChihiUniversity of LuxembourgArtificial intelligence is really the best solution for systems with unpredictable behavior? A comparative study between ANN and Multi-model approachdetails
2022.09.28Samuel RenaultLuxembourg Institute of Science and TechnologyAI Act: a grasp of the future EU regulation on AI and its impact on AI practitionersdetails
2022.09.21Alena KopanicakovaBrown UniversityMultilevel training of deep neural networksdetails
2022.07.06Guendalina PalmirottaEuropean Space AgencyMachine Learning in Space Weather and how to handle itdetails
2022.06.29Han ZhangUNSW SydneyArtificial Neural Network Method Based on Boundary Integral Equationsdetails
2022.06.22Fateme DarlikUniversity of LuxembourgUsing Physics-Informed constrained neural network to reconstruct the motion of the particles for time more than the training timedetails
2022.06.01Aishwarya KrishnanUniversity of LuxembourgDesign of a chat bot for service-now knowledge basedetails
2022.05.11Lorella ViolaUniversity of LuxembourgThe problem with GPT for the Humanities (and for humanity)details
2022.05.04Aubin GeoffreÉcole Mines de Saint-ÉtienneGaussian Process Regression with anisotropic kernel for supervised feature selection.details
2022.04.13Vu ChauUniversity of LuxembourgNon-parametric data-driven constitutive modelling using artificial neural networks.details
2022.03.16Alban OdotINRIA Strasbourg Deformation approximation : Improve your Artificial Neural Network training using the Finite Element Method formulation. A case for static deformations.details
2022.03.02Onkar JadhavUniversity of Luxembourg & SnTParametric model order reduction with an adaptive greedy sampling approach based on surrogate modeling. An application of the pMOR in financial risk analysis.details
2022.02.23Lester MackeyMicrosoft Research & Stanford UniversityKernel Thinning and Stein Thinningdetails
2022.02.16Ola RønningUniversity of CopenhagenELBO-within-Stein: General and integrated Stein Variational Inference (Part 3 of 3)details
2022.02.09Christian ThygesenEvaxion / University of CopenhagenEfficient generative modelling of protein structure fragments using a Deep Markov Model (Part 2 of 3)details
2022.02.02Thomas HamelryckUniversity of CopenhagenDeep probabilistic programming and the protein folding problem (Part 1 of 3)details
2022.01.26Ioannis KalogerisETH ZurichAccelerating the solution of parametrized partial differential equations using machine learning toolsdetails
2022.01.19Niccolo GentileUniversity of LuxembourgUnderstanding the determinants of well-being: a case study in interpretable machine learningdetails
2022.01.12Tjeerd V. olde ScheperOxford Brookes UniversityCriticality Analysis for Non-linear Data Representationdetails
2021.12.08Ayan ChakrabortyLeibniz University HannoverDeep neural network on PDEsdetails
2021.11.24Marharyta AleksandrovaUniversity of LuxembourgCausal Inference & Causal Learning: Towards Causal ML (Part 3 of 3)details
2021.11.17Fabio CuzzolinOxford Brookes UniversityThe epistemic artificial intelligence projectdetails
2021.11.10Marharyta AleksandrovaUniversity of LuxembourgCausal Inference & Causal Learning: Towards Causal ML (Part 2 of 3)details
2021.11.03Marharyta AleksandrovaUniversity of LuxembourgCausal Inference & Causal Learning: Towards Causal ML (Part 1 of 3)details
2021.10.27Vladimir DespotovicUniversity of LuxembourgMarkov Logic Networks: A step towards interpretable AIdetails
2021.10.20Paris PapavasileiouUniversity of LuxembourgA data-driven approach for the prediction and optimization of an industrial scale chemical vapour deposition processdetails
2021.10.06Soumianarayanan VijayaraghavanUniversity of LuxembourgNeural-network acceleration of projection-based model-order-reduction for finite plasticity: Application to RVEsdetails
2021.09.29Saurabh DeshpandeUniversity of LuxembourgSurrogate Deep Learning Framework for Real-Time Hyper-Elastic Simulations with Uncertaintiesdetails
2021.09.22Marharyta AleksandrovaUniversity of LuxembourgConformal Prediction – Machine Learning with Accuracy Guaranteesdetails
2021.09.15Mauro Dalle Lucca TosiUniversity of LuxembourgTensAIR: an asynchronous and decentralized framework to distribute artificial neural networks trainingdetails
2021.07.14Alessandro TemperoniUniversity of LuxembourgSecond-order methods for deep learningdetails
2021.07.07Juan Pineda-JaramilloUniversity of LuxembourgExploring significant predictors of freight rail intermodal operation delays using causal Machine Learningdetails
2021.06.30Maciej SkorskiUniversity of LuxembourgApproximating Hessians for Neural Networksdetails
2021.06.16Piergiorgio VitelloUniversity of LuxembourgEnhancing Public Transport Demand Information Using Crowdsourced Datadetails
2021.06.02Juntong ChenUniversity of LuxembourgRobust estimation of a regression function in exponential familiesdetails
2021.05.19Jimmy TekliBMW GROUP, Université de Franche-ComtéLeveraging Deep Learning-Assisted Attacks against Image Obfuscation via Federated Learningdetails
2021.05.12Fateme DarlikUniversity of LuxembourgNeural network supported surrogate models for particle-laden flowdetails
2021.05.05Anja LeistUniversity of LuxembourgA classification of machine learning approaches for the social and health sciencesdetails
2021.04.28Pavlos GkinisNational Technical University of AthensAcceleration of CFD calculations using Reduced-Order Modeling. Application in CVD processesdetails
2021.04.21Raphaël Couturier & Michel SalomonFEMTO-ST Institute, UBFC, CNRSSome applications of deep learning from image security, to medical image, through IoT physiological signaldetails
2021.04.14Hamidreza DehghaniUniversity of LuxembourgMultiscale Poro-Hyperelasticity using ANNsdetails
2021.04.07Hussein RappelThe Alan Turing InstituteProbabilistic modeling and identification of intercorrelated random fields with bounds: Application to linear elastic struts and fibersdetails
2021.03.31Hichem OmraniLuxembourg Institute of Socio-Economic ResearchPredicting air pollution using remote sensing and sensors measurementdetails
2021.03.24Gabriele PozzettiCERATIZITAn Industry view on ML: CERATIZIT technology landscape and the art of collaborating with an industrial partner.details
2021.03.17Damian Mingo NdiwagoUniversity of LuxembourgUncertainty precision and reliability of Ecohydrological models: Bayesian model selectiondetails
2021.03.10Igor PoltavskyiUniversity of LuxembourgMachine learning for molecular simulationsdetails
2021.02.24Carlotta MontorsiLuxembourg Institute of Socio-Economic ResearchTree based algorithms: implementing Conditional Inference Trees and Forest for old age Frailty Index predictionsdetails
2021.02.17Minh Vu ChauUniversity of LuxembourgData-driven constitutive laws for hyperelasticity modeling in eigenspace using algorithmic differentiation coupling fenics pytorch model application to rvesdetails
2021.02.10Zhiqiang ZhongUniversity of LuxembourgReinforcement Learning based Meta-path Design for Heterogeneous Graph Neural Networkdetails
2021.02.03Saurabh Deshpande & Milad ZeraatpishehUniversity of LuxembourgPractical implementation session on Neural Networksdetails
2021.01.27Arif Sinan UsluUniversity of LuxembourgThe effect of self-paced neurofeedback on EEG learning: An experimental setupdetails
2021.01.20Milad ZeraatpishehUniversity of LuxembourgBayesian neural networks and MC Dropout; ways to measure uncertainty in Deep learningdetails
2021.01.13Lars BeexUniversity of LuxembourgUnsupervised learning to select modes for reduced-order models of hyperelastoplasticity: application to RVEs details
2020.12.16Erkan OterkusUniversity of StrathclydeA Physics-guided Machine Learning Model Based on Peridynamicsdetails
2020.12.09Eleni KoronakiUniversity of LuxembourgFrom partial data to out-of-sample parameter and observation estimation with Diffusion Maps and Geometric Harmonicsdetails
2020.12.02Vivek OOmmenIndian Institute of Technology MadrasThe effectiveness of PINNs in solving inverse heat transfer problemsdetails
2020.11.25Anina ŠarkićUniversity of LuxembourgMachine Learning in Wind Engineeringdetails
2020.11.18Diego KozlowskiUniversity of LuxembourgMachine Learning on graphsdetails
2020.11.11Tittu MathewIndian Institute of Technology MadrasBayesian uncertainty quantification and model selectiondetails
2020.11.04Arnaud MazierUniversity of LuxembourgDecision Trees methods, an overview of the white-boxesdetails
2020.10.28Cosmin AnitescuBauhaus-Universität WeimarMethods Based on Artificial Neural Networks for the Solution of Partial Differential Equationsdetails
2020.10.21Eleni KoronakiUniversity of Luxembourg“Dinky, Dirty, Dynamic & Deceptive Data (1)”: An overview of hybrid machine learning and equation-based modellingdetails
2020.10.14Saurabh DeshpandeUniversity of LuxembourgData Driven Hyper-elastic Simulationsdetails
2020.10.07Vasilis KrokosUniversity of Cardiff & Synopsys-SimplewareBayesian Neural Networks for uncertainty estimation on regression problemsdetails