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.
Program
| Date | Speaker | Affiliation | Topic | |
|---|---|---|---|---|
| 2023.01.18 | Philippe Baratta | Aix-Marseille University and CPPM, Marseille, France | Statistical methods in observational Cosmology | details |
| 2023.01.11 | Haralampos Hatzikirou | Faculty of Mathematics, Khalifa University, United Arab Emirates | How can we make tumour predictions when we do not understand everything? | details |
| 2022.11.30 | Andres Posada Moreno | RWTH Aachen University | Concept-based explanations for convolutional neural networks | details |
| 2022.11.23 | David Wagg | University of Sheffield | A time-evolving digital twin tool for engineering dynamics applications | details |
| 2022.11.09 | Orhan Ermis | Luxembourg Institute of Science and Technology | A CNN-based Semi-Supervised Learning Approach for the Detection of SS7 Attacks | details |
| 2022.10.26 | Oscar Castro | Luxembourg Institute of Science and Technology | Multi-target Compiler for the Deployment of Machine Learning Models | details |
| 2022.10.05 | Inès Chihi | University of Luxembourg | Artificial intelligence is really the best solution for systems with unpredictable behavior? A comparative study between ANN and Multi-model approach | details |
| 2022.09.28 | Samuel Renault | Luxembourg Institute of Science and Technology | AI Act: a grasp of the future EU regulation on AI and its impact on AI practitioners | details |
| 2022.09.21 | Alena Kopanicakova | Brown University | Multilevel training of deep neural networks | details |
| 2022.07.06 | Guendalina Palmirotta | European Space Agency | Machine Learning in Space Weather and how to handle it | details |
| 2022.06.29 | Han Zhang | UNSW Sydney | Artificial Neural Network Method Based on Boundary Integral Equations | details |
| 2022.06.22 | Fateme Darlik | University of Luxembourg | Using Physics-Informed constrained neural network to reconstruct the motion of the particles for time more than the training time | details |
| 2022.06.01 | Aishwarya Krishnan | University of Luxembourg | Design of a chat bot for service-now knowledge base | details |
| 2022.05.11 | Lorella Viola | University of Luxembourg | The problem with GPT for the Humanities (and for humanity) | details |
| 2022.05.04 | Aubin Geoffre | École Mines de Saint-Étienne | Gaussian Process Regression with anisotropic kernel for supervised feature selection. | details |
| 2022.04.13 | Vu Chau | University of Luxembourg | Non-parametric data-driven constitutive modelling using artificial neural networks. | details |
| 2022.03.16 | Alban Odot | INRIA Strasbourg | Deformation approximation : Improve your Artificial Neural Network training using the Finite Element Method formulation. A case for static deformations. | details |
| 2022.03.02 | Onkar Jadhav | University of Luxembourg & SnT | Parametric model order reduction with an adaptive greedy sampling approach based on surrogate modeling. An application of the pMOR in financial risk analysis. | details |
| 2022.02.23 | Lester Mackey | Microsoft Research & Stanford University | Kernel Thinning and Stein Thinning | details |
| 2022.02.16 | Ola Rønning | University of Copenhagen | ELBO-within-Stein: General and integrated Stein Variational Inference (Part 3 of 3) | details |
| 2022.02.09 | Christian Thygesen | Evaxion / University of Copenhagen | Efficient generative modelling of protein structure fragments using a Deep Markov Model (Part 2 of 3) | details |
| 2022.02.02 | Thomas Hamelryck | University of Copenhagen | Deep probabilistic programming and the protein folding problem (Part 1 of 3) | details |
| 2022.01.26 | Ioannis Kalogeris | ETH Zurich | Accelerating the solution of parametrized partial differential equations using machine learning tools | details |
| 2022.01.19 | Niccolo Gentile | University of Luxembourg | Understanding the determinants of well-being: a case study in interpretable machine learning | details |
| 2022.01.12 | Tjeerd V. olde Scheper | Oxford Brookes University | Criticality Analysis for Non-linear Data Representation | details |
| 2021.12.08 | Ayan Chakraborty | Leibniz University Hannover | Deep neural network on PDEs | details |
| 2021.11.24 | Marharyta Aleksandrova | University of Luxembourg | Causal Inference & Causal Learning: Towards Causal ML (Part 3 of 3) | details |
| 2021.11.17 | Fabio Cuzzolin | Oxford Brookes University | The epistemic artificial intelligence project | details |
| 2021.11.10 | Marharyta Aleksandrova | University of Luxembourg | Causal Inference & Causal Learning: Towards Causal ML (Part 2 of 3) | details |
| 2021.11.03 | Marharyta Aleksandrova | University of Luxembourg | Causal Inference & Causal Learning: Towards Causal ML (Part 1 of 3) | details |
| 2021.10.27 | Vladimir Despotovic | University of Luxembourg | Markov Logic Networks: A step towards interpretable AI | details |
| 2021.10.20 | Paris Papavasileiou | University of Luxembourg | A data-driven approach for the prediction and optimization of an industrial scale chemical vapour deposition process | details |
| 2021.10.06 | Soumianarayanan Vijayaraghavan | University of Luxembourg | Neural-network acceleration of projection-based model-order-reduction for finite plasticity: Application to RVEs | details |
| 2021.09.29 | Saurabh Deshpande | University of Luxembourg | Surrogate Deep Learning Framework for Real-Time Hyper-Elastic Simulations with Uncertainties | details |
| 2021.09.22 | Marharyta Aleksandrova | University of Luxembourg | Conformal Prediction – Machine Learning with Accuracy Guarantees | details |
| 2021.09.15 | Mauro Dalle Lucca Tosi | University of Luxembourg | TensAIR: an asynchronous and decentralized framework to distribute artificial neural networks training | details |
| 2021.07.14 | Alessandro Temperoni | University of Luxembourg | Second-order methods for deep learning | details |
| 2021.07.07 | Juan Pineda-Jaramillo | University of Luxembourg | Exploring significant predictors of freight rail intermodal operation delays using causal Machine Learning | details |
| 2021.06.30 | Maciej Skorski | University of Luxembourg | Approximating Hessians for Neural Networks | details |
| 2021.06.16 | Piergiorgio Vitello | University of Luxembourg | Enhancing Public Transport Demand Information Using Crowdsourced Data | details |
| 2021.06.02 | Juntong Chen | University of Luxembourg | Robust estimation of a regression function in exponential families | details |
| 2021.05.19 | Jimmy Tekli | BMW GROUP, Université de Franche-Comté | Leveraging Deep Learning-Assisted Attacks against Image Obfuscation via Federated Learning | details |
| 2021.05.12 | Fateme Darlik | University of Luxembourg | Neural network supported surrogate models for particle-laden flow | details |
| 2021.05.05 | Anja Leist | University of Luxembourg | A classification of machine learning approaches for the social and health sciences | details |
| 2021.04.28 | Pavlos Gkinis | National Technical University of Athens | Acceleration of CFD calculations using Reduced-Order Modeling. Application in CVD processes | details |
| 2021.04.21 | Raphaël Couturier & Michel Salomon | FEMTO-ST Institute, UBFC, CNRS | Some applications of deep learning from image security, to medical image, through IoT physiological signal | details |
| 2021.04.14 | Hamidreza Dehghani | University of Luxembourg | Multiscale Poro-Hyperelasticity using ANNs | details |
| 2021.04.07 | Hussein Rappel | The Alan Turing Institute | Probabilistic modeling and identification of intercorrelated random fields with bounds: Application to linear elastic struts and fibers | details |
| 2021.03.31 | Hichem Omrani | Luxembourg Institute of Socio-Economic Research | Predicting air pollution using remote sensing and sensors measurement | details |
| 2021.03.24 | Gabriele Pozzetti | CERATIZIT | An Industry view on ML: CERATIZIT technology landscape and the art of collaborating with an industrial partner. | details |
| 2021.03.17 | Damian Mingo Ndiwago | University of Luxembourg | Uncertainty precision and reliability of Ecohydrological models: Bayesian model selection | details |
| 2021.03.10 | Igor Poltavskyi | University of Luxembourg | Machine learning for molecular simulations | details |
| 2021.02.24 | Carlotta Montorsi | Luxembourg Institute of Socio-Economic Research | Tree based algorithms: implementing Conditional Inference Trees and Forest for old age Frailty Index predictions | details |
| 2021.02.17 | Minh Vu Chau | University of Luxembourg | Data-driven constitutive laws for hyperelasticity modeling in eigenspace using algorithmic differentiation coupling fenics pytorch model application to rves | details |
| 2021.02.10 | Zhiqiang Zhong | University of Luxembourg | Reinforcement Learning based Meta-path Design for Heterogeneous Graph Neural Network | details |
| 2021.02.03 | Saurabh Deshpande & Milad Zeraatpisheh | University of Luxembourg | Practical implementation session on Neural Networks | details |
| 2021.01.27 | Arif Sinan Uslu | University of Luxembourg | The effect of self-paced neurofeedback on EEG learning: An experimental setup | details |
| 2021.01.20 | Milad Zeraatpisheh | University of Luxembourg | Bayesian neural networks and MC Dropout; ways to measure uncertainty in Deep learning | details |
| 2021.01.13 | Lars Beex | University of Luxembourg | Unsupervised learning to select modes for reduced-order models of hyperelastoplasticity: application to RVEs | details |
| 2020.12.16 | Erkan Oterkus | University of Strathclyde | A Physics-guided Machine Learning Model Based on Peridynamics | details |
| 2020.12.09 | Eleni Koronaki | University of Luxembourg | From partial data to out-of-sample parameter and observation estimation with Diffusion Maps and Geometric Harmonics | details |
| 2020.12.02 | Vivek OOmmen | Indian Institute of Technology Madras | The effectiveness of PINNs in solving inverse heat transfer problems | details |
| 2020.11.25 | Anina Šarkić | University of Luxembourg | Machine Learning in Wind Engineering | details |
| 2020.11.18 | Diego Kozlowski | University of Luxembourg | Machine Learning on graphs | details |
| 2020.11.11 | Tittu Mathew | Indian Institute of Technology Madras | Bayesian uncertainty quantification and model selection | details |
| 2020.11.04 | Arnaud Mazier | University of Luxembourg | Decision Trees methods, an overview of the white-boxes | details |
| 2020.10.28 | Cosmin Anitescu | Bauhaus-Universität Weimar | Methods Based on Artificial Neural Networks for the Solution of Partial Differential Equations | details |
| 2020.10.21 | Eleni Koronaki | University of Luxembourg | “Dinky, Dirty, Dynamic & Deceptive Data (1)”: An overview of hybrid machine learning and equation-based modelling | details |
| 2020.10.14 | Saurabh Deshpande | University of Luxembourg | Data Driven Hyper-elastic Simulations | details |
| 2020.10.07 | Vasilis Krokos | University of Cardiff & Synopsys-Simpleware | Bayesian Neural Networks for uncertainty estimation on regression problems | details |