ESANN 2023 programme

Wednesday, 04.10.2023

09:00 Welcome session

09:10 Graph Representation Learning
Organized by: Federico Errica, Davide Bacciu, Alessio Micheli, Luca Pasa, Nicolò Navarin, Marco Podda, Daniele Zambon

09:10 Graph Representation Learning

  • Davide Bacciu, University of Pisa (Italy)
  • Federico Errica, NEC Laboratories Europe GmbH (Germany)
  • Alessio Micheli, Università di Pisa (Italy)
  • Nicolò Navarin, University of Padua (Italy)
  • Luca Pasa, University of Padova (Italy)
  • Marco Podda, Università di Pisa (Italy)
  • Daniele Zambon, The Swiss AI Lab IDSIA (Switzerland)

09:30 Richness of Node Embeddings in Graph Echo State Networks

  • Domenico Tortorella, University of Pisa (Italy)
  • Alessio Micheli, Università di Pisa (Italy)

09:50 An Empirical Study of Over-Parameterized Neural Models based on Graph Random Features

  • Nicolò Navarin, University of Padua (Italy)
  • Luca Pasa, University of Padova (Italy)
  • Luca Oneto, University of Genoa (Italy)
  • Alessandro Sperduti, University of Padua (Italy)

10:10 Convolutional Transformer via Graph Embeddings for Few-shot Toxicity and Side Effect Prediction

  • Luis Torres, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Bernardete Ribeiro, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
  • Joel Arrais, Department of Informatics Engineering (DEI), Center for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)

10:30 Hidden Markov Models for Temporal Graph Representation Learning

  • Federico Errica, NEC Laboratories Europe GmbH (Germany)
  • Alessio Gravina, University of Pisa (Italy)
  • Davide Bacciu, University of Pisa (Italy)
  • Alessio Micheli, Università di Pisa (Italy)

10:50 Graph Representation Learning - Poster spotlights
Organized by: Federico Errica, Davide Bacciu, Alessio Micheli, Luca Pasa, Nicolò Navarin, Marco Podda, Daniele Zambon

10:50 A Tropical View of Graph Neural Networks

  • Francesco Landolfi, Università di Pisa (Italy)
  • Davide Bacciu, University of Pisa (Italy)
  • Danilo Numeroso, University of Pisa (Italy)

10:51 Graph-based Categorical Embedding

  • Weiwei Wang, Maastricht University (Netherlands)
  • Stefano Bromuri, Open University (Netherlands)
  • Michel Dumontier, Maastricht University (Netherlands)

10:52 FouriER: Link Prediction by Mixing Tokens with Fourier-enhanced MetaFormer

  • Thanh Vu, Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam Vietnam National University, Ho Chi Minh City, Vietnam (Vietnam)
  • Huy Ngo, Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam Vietnam National University, Ho Chi Minh City, Vietnam (Vietnam)
  • Bac Le, Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam Vietnam National University, Ho Chi Minh City, Vietnam (Vietnam)
  • Thanh Le, University of Science, Vietnam National University, Ho Chi Minh City, Vietnam (Vietnam)

10:53 Coffree break

11:20 Feature selection and dimension reduction

11:20 Feature Selection for Concept Drift Detection

  • Fabian Hinder, Cognitive Interaction Technology (CITEC), Bielefeld University (Germany)
  • Barbara Hammer, Cognitive Interaction Technology (CITEC), Bielefeld University (Germany)

11:40 Improved Interpretation of Feature Relevances: Iterated Relevance Matrix Analysis (IRMA)

  • Michael Biehl, University of Groningen, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence (The Netherlands)
  • Sofie Lövdal, University Medical Center Groningen (UMCG), Department of Nuclear Medicine and Molecular Imaging Hanzeplein 1, 9713 GZ Groningen -The Netherlands (The Netherlands)

12:00 Sparse Nyström Approximation for Non-Vectorial Data Using Class-informed Landmark Selection

  • Maximilian Münch, University of Applied Sciences Würzburg-Schweinfurt University of Groningen (Germany)
  • Katrin Sophie Bohnsack, University of Applied Sciences Mittweida (Germany)
  • Alexander Engelsberger, University of Applied Sciences Mittweida, Saxon Institute for Computational Intelligence (Deutschland)
  • Frank-Michael Schleif, Technical University of Applied Sciences Würzburg-Schweinfurt (Germany)
  • Thomas Villmann, Mittweida University of Applied Sciences, Saxon Institute for Computational Intelligence and Machine Learning (Germany)

12:20 Improved the locally aligned ant technique (LAAT) strategy to recover manifolds embedded in strong noise

  • Felipe Contreras, University of Groningen - Kapteyn Astronomical Institute (Netherlands)
  • Kerstin Bunte, University of Groningen (Netherlands)
  • Reynier Peletier, University of Groningen (The Netherlands)

12:40 Feature selection and dimension reduction - Poster spotlights

12:40 Nesterov momentum and gradient normalization to improve t-SNE convergence and neighborhood preservation, without early exaggeration

  • Pierre Lambert, UCLouvain (Belgium)
  • John Lee, UCLouvain (Belgium)
  • Edouard Couplet, UCLouvain (Belgique)
  • Cyril de Bodt, UCLouvain - ICTEAM (Belgium)

12:42 Robust Feature Selection and Robust Training to Cope with Hyperspectral Sensor Shifts

  • Valerie Vaquet, CITEC, Bielefeld University (Germany)
  • Johannes Brinkrolf, CITEC - Cognitive Interaction Technology Bielefeld University (Germany)
  • Barbara Hammer, CITEC - Bielefeld University (Germany)

12:43 A Counterexample to Ockham's Razor and the Curse of Dimensionality: Marginalising Complexity and Dimensionality for GMMs

  • Benoit Frénay, Université de Namur (Belgium)

12:44 Feature Selection for Multi-label Classification with Minimal Learning Machine

  • Joakim Linja, University of Jyväskylä Faculty of Information Techonolgy (Finland)
  • Joonas Hämäläinen, University of Jyväskylä, Faculty of Information Technology (Finland)
  • Tommi Kärkkäinen, University of Jyvaskyla, Faculty of Information Technology (Finland)

12:45 Learning with Boosting Decision Stumps for Feature Selection in Evolving Data Streams

  • Daniel Nowak-Assis, Independent Researcher (Brazil)

12:46 Lunch

14:10 Towards Machine Learning Models that We Can Trust: Testing, Improving, and Explaining Robustness
Organized by: Maura Pintor, Ambra Demontis, Battista Biggio

14:10 Towards Machine Learning Models that We Can Trust: Testing, Improving, and Explaining Robustness

  • Maura Pintor, University of Cagliari (Italy)
  • Ambra Demontis, University of Cagliari (Italy)
  • Battista Biggio, University of Cagliari (Italy)

14:30 Secure Federated Learning with Kernel Affine Hull Machines

  • Mohit Kumar, Software Competence Center Hagenberg GmbH (Austria)
  • Bernhard Moser, Software Competence Center Hagenberg GmbH (Austria)
  • Lukas Fischer, Software Competence Center Hagenberg GmbH (Austria)

14:50 Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization

  • Giorgio Piras, University of Cagliari (Italy)
  • Giuseppe Floris, University of Cagliari (Italy)
  • Raffaele Mura, University of Cagliari (Italia)
  • Luca Scionis, University of Cagliari (Italy)
  • Maura Pintor, University of Cagliari (Italy)
  • Battista Biggio, University of Cagliari (Italy)
  • Ambra Demontis, University of Cagliari (Italy)

15:10 Towards Machine Learning Models that We Can Trust: Testing, Improving, and Explaining Robustness - Poster spotlights
Organized by: Maura Pintor, Ambra Demontis, Battista Biggio

15:10 On the Limitations of Model Stealing with Uncertainty Quantification Models

  • David Pape, CISPA Helmholtz Center for Information Security (Germany)
  • Sina Däubener, Ruhr University Bochum (please complete)
  • Thosten Eisenhofer, Ruhr University Bochum (Germany)
  • Antonio Emanuele Cinà, CISPA Helmholtz Center for Information Security (Germany)
  • Lea Schönherr, CISPA Helmholtz Center for Information Security (Germany)

15:11 Towards Randomized Algorithms and Models that We Can Trust: a Theoretical Perspective

  • Luca Oneto, University of Genoa (Italy)
  • Sandro Ridella, University of Genoa (Italy)
  • Davide Anguita, DIBRIS - University of Genova (Italy)

15:12 Single-pass uncertainty estimation with layer ensembling for regression: application to proton therapy dose prediction for head and neck cancer

  • Ana Maria Barragan Montero, UCLouvain (Belgium)
  • Robin Tilman, UCLouvain (Belgium)
  • Margerie Huet-Dastarac, UCLouvain (Belgium)
  • John Lee, UCLouvain (Belgium)

15:13 Fairness and Interpretability, Clustering, and NLP

15:13 Mixture of stochastic block models for multiview clustering

  • Kylliann De Santiago, Laboratoire de Mathématiques et Modélisation d'Évry (UMR 8071) (France)
  • Marie Szafranski, École Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (France)
  • Christophe Ambroise, Laboratoire de Mathématiques et Modélisation d'Évry (France)

15:33 Fine-tuning is not (always) overfitting artifacts

  • Jérémie Bogaert, UCLouvain - ICTEAM (Belgium)
  • Emmanuel Jean, Multitel (Belgium)
  • Cyril de Bodt, UCLouvain - ICTEAM (Belgium)
  • François-Xavier Standaert, UCLouvain - ICTEAM (Belgium)

15:53 On Instance Weighted Clustering Ensembles

  • Paul Moggridge, University of Hertfordshire, UK (UK)
  • Na Helian, University of Hertfordshire, UK (UK)
  • Yi Sun, University of Hertfordshire, UK (UK)
  • Mariana Lilley, University of Hertfordshire, UK (UK)

16:13 Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis

  • Zhengxiang Shi, University College London (United Kingdom)
  • Aldo Lipani, UCL (United Kingdom)

16:33 Fairness and Interpretability, Clustering, and NLP - Poster spotlights

16:33 Similarity versus Supervision: Best Approaches for HS Code Prediction

  • Sédrick Stassin, University of Mons (UMONS) (Belgique)
  • otmane Amel, University of Mons (Belgique)
  • Sidi Ahmed Mahmoudi, UMONS (Belgium)
  • Xavier Siebert, UMONS (Belgique)

16:34 Multimodal Approach for Harmonized System Code Prediction

  • otmane Amel, University of Mons (Belgique)
  • Sédrick Stassin, University of Mons (UMONS) (Belgique)
  • Sidi Ahmed Mahmoudi, UMONS (Belgium)
  • Xavier Siebert, UMONS (Belgique)

16:35 Mitigating Robustness Bias: Theoretical Results and Empirical Evidences

  • Danilo Franco, University of Genoa (Italy)
  • Luca Oneto, University of Genoa (Italy)
  • Davide Anguita, DIBRIS - University of Genova (Italy)

16:36 End-to-End Neural Network Training for Hyperbox-Based Classification

  • Denis Martins, University of Münster (Germany)
  • Christian Lülf, University of Münster (Germany)
  • Fabian Gieseke, University of Münster (Germany)

16:37 TabSRA: An Attention based Self-Explainable Model for Tabular Learning

  • Kodjo Mawuena AMEKOE, LIPN, University Paris 13 BPCE SA (France)
  • Mohamed Djallel DILMI, LIPN, University Paris 13 Hanane AZZAG, LIPN, University Paris 13 (France)
  • Zaineb CHELLY DAGDIA, UVSQ, Paris-Saclay (France)
  • Mustapha Lebbah, Université Paris-Saclay - UVSQ Versailles Campus (France)
  • Grégoire JAFFRE, Groupe BPCE

16:38 Improving Fairness via Intrinsic Plasticity in Echo State Networks

  • Andrea Ceni, University of Pisa (Italy)
  • Davide Bacciu, University of Pisa (Italy)
  • Valerio De Caro, University of Pisa (Italy)
  • Claudio Gallicchio, University of Pisa (Italy)
  • Luca Oneto, University of Genoa (Italy)

16:39 Is Boredom an Indicator on the way to Singularity of Artificial Intelligence? Hypotheses as Thought-Provoking Impulse

  • Martin Bogdan, Leipzig University (Germany)

16:40 Adversarial Auditing of Machine Learning Models under Compound Shift

  • Karan Bhanot, Rensselaer Polytechnic Institute (United States)
  • Dennis Wei, IBM Research (USA)
  • Ioana Baldini
  • Kristin Bennett, Rensselaer Polytechnic Institute (United States)

16:41 Language Modeling in Logistics: Customer Calling Prediction

  • Xi Chen, Open university of the Netherlands (Netherlands)
  • Giacomo Anerdi, Maastricht University (The Netherlands)
  • Daniel Tan
  • Stefano Bromuri, Open University (Netherlands)

16:42 Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability

  • Indro Spinelli, Sapienza University of Rome (Italy)
  • Michele Guerra, UiT The Arctic University of Norway (Norway)
  • Filippo Maria Bianchi, NORCE - the Norwegian Research Center (Norway)
  • Simone Scardapane, Sapienza University of Rome (Italia)

16:43 Coffee break and poster exhibition

18:15 Walking tour of Bruges with guides

 

Thursday, 05.10.2023

09:00 Quantum Artificial Intelligence
Organized by: José D. Martín-Guerrero, Lucas Lamata, Thomas Villmann

09:00 Quantum Artificial Intelligence: A tutorial

  • José D. Martín-Guerrero, Universitat de València (Spain)
  • Lucas Lamata, Universidad de Sevilla (Spain)
  • Thomas Villmann, Mittweida University of Applied Sciences, Saxon Institute for Computational Intelligence and Machine Learning (Germany)

09:20 Quantum Feature Selection with Variance Estimation

  • Alessandro Poggiali, University of Pisa (Italy)
  • Anna Bernasconi, Università di Pisa (Itaky)
  • Alessandro Berti, University of Pisa (Italy)
  • Gianna Del Corso, Dept Computer science, university of Pisa (Italy)
  • Riccardo Guidotti, University of Pisa (Italia)

09:40 Logarithmic Quantum Forking

  • Alessandro Berti, University of Pisa (Italy)

10:00 Quantum Artificial Intelligence - Poster spotlights
Organized by: José D. Martín-Guerrero, Lucas Lamata, Thomas Villmann

10:00 Quantum-ready vector quantization: Prototype learning as a binary optimization problem

  • Alexander Engelsberger, University of Applied Sciences Mittweida, Saxon Institute for Computational Intelligence (Deutschland)
  • Thomas Villmann, Mittweida University of Applied Sciences, Saxon Institute for Computational Intelligence and Machine Learning (Germany)

10:01 Potential analysis of a Quantum RL controller in the context of autonomous driving

  • M. Lautaro Hickmann, Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR) - Institut für KI-Sicherheit (Germany)
  • Arne Raulf, Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR) - Institut für KI-Sicherheit (Germany)
  • Frank Köster, Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR) - Institut für KI-Sicherheit (Germany)
  • Friedhelm Schwenker, Ulm University (Germany)
  • Hans-Martin Rieser, Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR) - Institut für KI-Sicherheit (Germany)

10:02 Green Machine Learning
Organized by: Verónica Bolón-Canedo, Laura Morán-Fernández, Brais Cancela, Amparo Alonso-Betanzos

10:02 Green Machine Learning

  • Verónica Bolón-Canedo, CITIC, Universidade da Coruña (Spain)
  • Laura Morán-Fernández, CITIC, Universidade da Coruña (Spain)
  • Brais Cancela, Universidade da Coruña (Spain)
  • Amparo Alonso-Betanzos, CITIC, Universidade da Coruña (Spain)

10:22 Logarithmic division for green feature selection: an information-theoretic approach

  • Samuel Suárez-Marcote, CITIC, Universidade da Coruña (Spain)
  • Laura Morán-Fernández, CITIC, Universidade da Coruña (Spain)
  • Verónica Bolón-Canedo, CITIC, Universidade da Coruña (Spain)

10:42 Green Machine Learning - Poster spotlights
Organized by: Verónica Bolón-Canedo, Laura Morán-Fernández, Brais Cancela, Amparo Alonso-Betanzos

10:42 Efficient feature selection for domain adaptation using Mutual Information Maximization

  • Guillermo Castillo García, Universidade da Coruña (Spain)
  • Laura Morán-Fernández, CITIC, Universidade da Coruña (Spain)
  • Verónica Bolón-Canedo, CITIC, Universidade da Coruña (Spain)

10:43 Automated green machine learning for condition-based maintenance

  • Afonso Lourenco, Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Polytechnic of Porto, Portugal (PORTUGAL)
  • Carolina Ferraz, GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Polytechnic of Porto, Portugal (Portugal)
  • Jorge Meira, ISEP (Portugal)
  • Goreti Marreiros, Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Polytechnic of Porto, Portugal (Portugal)
  • Verónica Bolón-Canedo, CITIC, Universidade da Coruña (Spain)
  • Amparo Alonso-Betanzos, CITIC, Universidade da Coruña (Spain)

10:44 Multispectral Texture Classification in Agriculture

  • Mariya Shumska, University of Groningen (the Netherlands)
  • Kerstin Bunte, University of Groningen (The Netherlands)

10:45 Coffee break

11:10 Reinforcement learning and Evolutionary computation

11:10 DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety

  • André Correia, Universidade da Beira Interior and NOVA LINCS (Portugal)
  • Luís Alexandre, Universidade da Beira Interior and NOVA LINCS (Portugal)

11:30 Automatic Trade-off Adaptation in Offline RL

  • Phillip Swazinna, Siemens AG / TU Munich (Germany)
  • Steffen Udluft, Siemens Technology (Germany)
  • Thomas Runkler, Siemens AG/ TU Munich (Germany)

11:50 Enhancing Evolution Strategies with Evolution Path Bias

  • Oliver Kramer, University of Oldenburg (Germany)

12:10 Multi-Fidelity Reinforcement Learning with Control Variates

  • Sami Khairy, Microsoft (Canada)
  • Prasanna Balaprakash, Oak Ridge National Laboratory (United States)

12:30 Reinforcement learning and Evolutionary computation - Poster spotlights

12:30 Sun Tracking using a Weightless Q-Learning Neural Network

  • Guilherme Souza, Universidade Federal do Rio de Janeiro (Brazil)
  • Priscila Lima, Universidade Federal do Rio de Janeiro (Brazil)
  • Felipe França, Instituto de Telecomunicações (Portugal)

12:31 A model-based approach to meta-Reinforcement Learning: Transformers and tree search

  • Brieuc Pinon, Université Catholique de Louvain ICTEAM/INMA (Belgium)
  • Raphaël Jungers, Université Catholique de Louvain ICTEAM/INMA (Belgium)
  • Jean-Charles Delvenne, Université Catholique de Louvain ICTEAM/INMA (Belgium)

12:32 Derivative-Free Optimization Approaches for Force Polytopes Prediction

  • Gautier Laisné, INRIA de l'Université de Bordeaux, project team AUCTUS (France)
  • Nasser Rezzoug, PPrime Institute, CNRS, University of Poitiers, ENSMA, UPR 3346 (France)
  • Jean-Marc Salotti, University of Bordeaux, CNRS, Bordeaux INP, IMS, UMR 5218, F-33400 (France)

12:33 Policy-Based Reinforcement Learning in the Generalized Rock-Paper-Scissors Game

  • Imre Gergely Mali, Babeș-Bolyai University (Romania)
  • Gabriela Czibula, Babeș-Bolyai University (Romania)

12:34 Classification - poster spotlights

12:34 Performance Evaluation of Activation Functions in Extreme Learning Machine

  • Karol Struniawski, Institute of Information Technology, Warsaw University of Life Sciences - SGGW (Polska)
  • Aleksandra Konopka, Institute of Information Technology, Warsaw University of Life Sciences - SGGW (Polska)
  • Ryszard Kozera, Institute of Information Technology, Warsaw University of Life Sciences - SGGW (Polska)

12:35 Evaluating Curriculum Learning Strategies for Pancreatic Cancer Prediction

  • Eduardo Mosqueira-Rey, Universidade da Coruña (España)
  • David Vázquez-Lema, Universidade da Coruña (España)
  • Elena Hernández-Pereira, Universidade da Coruña (Spain)

12:36 Improving the DRASiW performance by exploiting its own "Mental Images"

  • Gianluca Coda, CNR
  • Massimo De Gregorio, CNR (Italy)
  • Antonio Sorgente, CNR (Italia)
  • Paolo Vanacore, CNR

12:37 Efficient Knowledge Aggregation Methods for Weightless Neural Networks

  • Otávio Napoli, UNICAMP (Brazil)
  • Ana Maria de Almeida, ISCTE - Instituto Universitário de Lisboa (ISTAR) (Portugal)
  • José Miguel Sales Dias, ISCTE - Instituto Universitário de Lisboa (ISTAR) (Portugal)
  • Luís Brás Rosário, Faculty of Medicine, Lisbon University (Portugal)
  • Edson Borin, UNICAMP - Institute of Computing (Brazil)
  • Mauricio Breternitz Jr., Instituto Universitario de Lisboa (Portugal)

12:38 Learning Vector Quantization in Context of Information Bottleneck Theory

  • Mehrdad Mohannazadeh Bakhtiari, University of Applied Sciences Mittweida, Saxon Institute for Compuational Intelligence and Machine Learning (Deutschland)
  • Daniel Staps, UAS Mittweida - SICIM (Germany)
  • Thomas Villmann, Mittweida University of Applied Sciences, Saxon Institute for Computational Intelligence and Machine Learning (Germany)

12:39 SOM-based Classification and a Novel Stopping Criterion for Astroparticle Applications

  • Luis Sanchez, Rice University (USA)
  • Erzsébet Merényi, Rice University (USA)
  • Christopher Tunnell, Rice University (U.S.A)

12:40 WiSARD-based Ensemble Learning

  • Leopoldo Lusquino Filho, São Paulo State University/ Institute of Science and Technology of Sorocaba (Brazil)
  • Felipe França, Instituto de Telecomunicações (Portugal)
  • Priscila Lima, Universidade Federal do Rio de Janeiro (Brazil)

12:41 Lunch

14:10 Deep learning and Computer vision

14:10 Entropy Based Regularization Improves Performance in the Forward-Forward Algorithm

  • Matteo Pardi, University of Pisa (Italy)
  • Domenico Tortorella, University of Pisa (Italy)
  • Alessio Micheli, Università di Pisa (Italy)

14:30 On the number of latent representations in deep neural networks for tabular data

  • Edouard Couplet, UCLouvain (Belgique)
  • Pierre Lambert, UCLouvain (Belgium)
  • Michel Verleysen, UCLouvain - ICTEAM institute (Belgium)
  • John Lee, UCLouvain (Belgium)
  • Cyril de Bodt, UCLouvain - ICTEAM (Belgium)

14:50 CRE: Circle relationship embedding of patches in vision transformer

  • Zhengyang Yu, Frankfurt Institute for Advanced Studies (FIAS) (Germany)
  • Jochen Triesch, Frankfurt Institute for Advanced Studies and Goethe-Universität Frankfurt (Germany)

15:10 Introducing Convolutional Channel-wise Goodness in Forward-Forward Learning

  • Andreas Papachristodoulou, KIOS CoE, University of Cyprus (Cyprus)
  • Christos Kyrkou, KIOS CoE, University of Cyprus (Cyprus)
  • Stelios Timotheou, Department of Electrical and Computer Engineering and KIOS Research and Innovation Center of Excellence, University of Cyprus (Cyprus)
  • Theocharis Theocharides, KIOS CoE, Department of Electrical and Computer Engineering, University of Cyprus (Cyprus)

15:30 An Alternating Minimization Algorithm with Trajectory for Direct Exoplanet Detection

  • Hazan Daglayan, ICTEAM Institute, UCLouvain (Belgium)
  • Simon Vary, ICTEAM Institute, UCLouvain (Belgium)
  • Pierre-Antoine Absil, UCLouvain (Belgium)

15:50 On Transformer Autoregressive Decoding for Multivariate Time Series Forecasting

  • Mohammed Aldosari, University of Georgia (United States)
  • John Miller, University of Georgia (United States)

16:10 Don’t waste SAM

  • Nermeen Abou Baker, Hochschule Ruhr West (Germany)
  • Uwe Handmann, Hochschule Ruhr West (Germany)

16:30 Deep learning and Computer vision - Poster Spotlights

16:30 Layered Neural Networks with GELU Activation, a Statistical Mechanics Analysis

  • Frederieke Richert, University of Groningen (The Netherlands)
  • Michiel Straat, Bielefeld University (Germany)
  • Elisa Oostwal, University of Groningen (The Netherlands)
  • Michael Biehl, University of Groningen, Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence (The Netherlands)

16:31 Real-time Detection of Evoked Potentials by Deep Learning: a Case Study

  • Leonardo Amato, Department of Mathematics "Tullio Levi-Civita'' (Italia)
  • Marta Maschietto, Department of Biomedical Sciences University of Padua (Italia)
  • Alessandro Leparulo, Department of Biomedical Sciences University of Padua (Italia)
  • Mattia Tambaro, Department of Biomedical Sciences University of Padua (Italia)
  • Stefano Vassanelli, Department of Biomedical Sciences and Padua Neuroscience Center University of Padua (Italia)
  • Alessandro Sperduti, University of Padua (Italy)

16:32 Coordinate descent on the Stiefel manifold for deep neural network training

  • Estelle Massart, UCLouvain (Belgium )
  • Vinayak Abrol, IIIT Delhi (Indian)

16:33 Action-Based ADHD Diagnosis in Video

  • Yichun Li, Newcastle University (United Kingdom)
  • Yuxing Yang, Newcastle University (United Kingdom)
  • Rajesh Nair, Cumbria, Northumberland, Tyne and Wear (CNTW), NHS Foundation Trust (United Kingdom)
  • Mohsen Naqvi, Newcastle University (United Kingdom)

16:34 Hierarchical priors for Hyperspherical Prototypical Networks

  • Samuele Fonio, Università degli studi di Torino (Italy)
  • Lorenzo Paletto, Università degli studi di Torino (Italy)
  • Mattia Cerrato, Johannes Gutenberg-Universitat Mainz (Germany)
  • Dino Ienco, INRAE (France)
  • Roberto Esposito, Università degli studi di Torino (Italy)

16:35 Segmentation and Analysis of Lumbar Spine MRI Scans for Vertebral Body Measurements

  • Helen Schneider, Fraunhofer IAIS (Germany)
  • David Biesner, Fraunhofer IAIS (Germany)
  • Akash Ashokan, Fraunhofer IAIS (Germany)
  • Maximilian Broß, Fraunhofer IAIS (Germany)
  • Rebecca Kador, Fraunhofer IAIS (Germany)
  • Sandra Halscheidt, Fraunhofer IAIS (Germany)
  • Gabor Bagyo, Evidia GmbH (Deutschland)
  • Peter Dankerl, Evidia MVZ Radiologie Franken GmbH (Deutschland)
  • Haissam Ragab, Diagnostic and Interventional Radiology University Medical Center Hamburg-Eppendorf (Deutschland )
  • Jin Yamamura, Evidia GmbH (Deutschland)
  • Christoph Labisch, Evidia GmbH (Deutschland)
  • Rafet Sifa, Fraunhofer IAIS & Fraunhofer Center for Machine Learning (Deutschland)

16:36 Retinal blood vessel segmentation from high resolution fundus image using deep learning architecture

  • henda boudegga, Medical Technology and Image Processing Laboratory, Univ. of Monastir, Tunisia. ISITCom Hammam-Sousse, University of Sousse, Tunisia. (Tunisie)
  • Yaroub Elloumi, ISITCom Hammam-Sousse, University of Sousse, Tunisia. Medical Technology and Image Processing Laboratory, Univ. of Monastir, Tunisia. (Tunisie)
  • Asma Ben Abdallah, Medical Technology and Image Processing Laboratory, Univ. of Monastir, Tunisia. (Tunisia)
  • Rostom Kachouri, LIGM, Univ. Gustave Eiffel, CNRS, ESIEE (France)
  • Mouhamed hédi Bedoui

16:37 Graph for Transformer Feature: A New Approach for Face Anti-Spoofing

  • Quoc-Huy Trinh, University of Science, VNU-HCM (Vietnam)
  • Hieu Nguyen, University of Science, VNU-HCM (Vietnam)
  • Van Nguyen, University of Science, VNU-HCM (Vietnam)
  • Xuan-Mao Nguyen, VNG Corporation (Vietnam)
  • Hai-Dang Nguyen, University of Science, VNU-HCM (Vietnam)

16:38 Temporal Ensembling-based Deep k-Nearest Neighbours for Learning with Noisy Labels

  • Alexandra-Ioana Albu, Babeș-Bolyai University (Romania)

16:39 Evaluation of Contrastive Learning for Electronic Component Detection

  • Leandro Silva, Universidade de Pernambuco - Escola Politécnica de Pernambuco Instituto Federal de Educação Ciência e Tecnologia da Paraíba (IFPB) (Brazil)
  • Agostinho Freire, Universidade de Pernambuco - Escola Politécnica de Pernambuco (Brazil)
  • Bruno Fernandes, Universidade de Pernambuco - Escola Politécnica de Pernambuco (Brazil)
  • George Azevedo, Universidade de Pernambuco (Brazil)
  • Sérgio Oliveira, Universidade de Pernambuco - Escola Politécnica de Pernambuco (Brazil)

16:40 Coffee break and poster exhibition

18:45 Visit of the "Halve maan" brewery

19:30 Conference dinner at the "Halve Maan" brewery

 

Friday, 06.10.2023

09:00 Sequential data, and Meta-learning

09:00 Revisiting the Mark Conditional Independence Assumption in Neural Marked Temporal Point Processes

  • Tanguy Bosser, University of Mons, Belgium (Belgium)
  • Souhaib Ben Taieb, University of Mons (Belgium)

09:20 A Protocol for Continual Explanation of SHAP

  • Andrea Cossu, University of Pisa (Italy)
  • Francesco Spinnato, Scuola Normale Superiore (Italy)
  • Riccardo Guidotti, University of Pisa (Italia)
  • Davide Bacciu, University of Pisa (Italy)

09:40 Residual Reservoir Computing Neural Networks for Time-series Classification

  • Claudio Gallicchio, University of Pisa (Italy)
  • Andrea Ceni, University of Pisa (Italy)

10:00 Probabilistic Adaptation for Meta-Learning

  • Tameem Adel, NPL (United Kingdom)

10:20 Sequential data, and Meta-learning - Poster spotlights

10:20 A hidden Markov model with Hawkes process-derived contextual variables to improve time series prediction. Case study in medical simulation.

  • Fatoumata Dama, Nantes Digital Science Laboratory (LS2N / UMR CNRS 6004) Nantes University (France)
  • Christine Sinoquet, Nantes Digital Science Laboratory (LS2N / UMR CNRS 6004) Nantes University (France)
  • Corinne Lejus-Bourdeau, Nantes University Hospital (France)

10:21 Deep dynamic co-clustering of streams of count data: a new online Zip-dLBM

  • Giulia Marchello, Université Côte d'Azur (France)
  • Marco Corneli, Université Côte d'Azur
  • Charles Bouveyron

10:22 Communication-Efficient Ridge Regression in Federated Echo State Networks

  • Valerio De Caro, University of Pisa (Italy)
  • Antonio Di Mauro, University of Pisa (Italy)
  • Davide Bacciu, Università di Pisa (Italy)
  • Claudio Gallicchio, University of Pisa (Italy)

10:23 Simultaneous failures classification in a predictive maintenance case

  • Antoine Hubermont, UNamur Telespazio Belgium (Belgium)
  • elio tuci, University of Namur (Belgium)
  • Nicola De Quattro, Telespazio Belgium (Belgium)

10:24 Hybrid modelling of dynamic anaerobic digestion process in full-scale with LSTM NN and BMP measurements

  • Alberto Meola, DBFZ Deutsches Biomasseforschungszentrum gGmbH (Germany)
  • Sören Weinrich, Münster University of Applied Sciences (Germany)

10:25 Wind Power Prediction with ETSformer

  • Oliver Kramer, University of Oldenburg (Germany)
  • Jill Baumann, University of Oldenburg (Germany)

10:26 Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?

  • Romain Egele, Argonne National Laboratory and Université Paris-Saclay (France)
  • Isabelle Guyon, Université Paris-Saclay (France)
  • Yixuan Sun, Argonne National Laboratory (United States)
  • Prasanna Balaprakash, Oak Ridge National Laboratory (United States)

10:27 Coffee break

10:55 Machine Learning Applied to Sign Language
Organized by: Benoit Frénay, Joni Dambre, Jérôme Fink, Mathieu De Coster

10:55 Trends and Challenges for Sign Language Recognition with Machine Learning

  • Jérôme Fink, University of Namur (Belgium)
  • Mathieu De Coster, IDLab-AIRO -- Ghent University -- imec (Belgium)
  • Joni Dambre, Ghent University - imec - IDLab (Belgium)
  • Benoit Frénay, Université de Namur (Belgium)

11:15 Multimodal Recognition of Valence, Arousal and Dominance via Late-Fusion of Text, Audio and Facial Expressions

  • Fabrizio Nunnari, German Research Center for Artificial Intelligence (DFKI) (Germany)
  • Annette Rios, University of Zurich, Department of Computational Linguistics (Switzerland)
  • Uwe Reichel, audEERING GmbH (Germany)
  • Chirag Bhuvaneshwara, German Research Center for Artificial Intelligence (DFKI), Saarland Informatics Campus, D3.2 (Germany)
  • Panagiotis Filntisis, ATHENA Research Center (Greece)
  • Petros Maragos, ATHENA Research Center (Greece)
  • Felix Burkhardt, audEERING GmbH (Germany)
  • Florian Eyben, audEERING GmbH (Germany)
  • Björn Schuller, audEERING GmbH (Germany)
  • Sarah Ebling, University of Zurich, Department of Computational Linguistics (Switzerland)

11:35 Exploring Strategies for Modeling Sign Language Phonology

  • Lee Kezar, University of Southern California (USA)
  • Tejas Srinivasan, University of Southern California (United States)
  • Riley Carlin, University of Southern California (United States)
  • Jesse Thomason, University of Southern California (United States)
  • Zed Sevcikova Sehyr, Chapman University (United States)
  • Naomi Caselli, Boston University (United States)

11:55 Machine Learning Applied to Sign Language - Poster spotlights
Organized by: Benoit Frénay, Joni Dambre, Jérôme Fink, Mathieu De Coster

11:55 Exploring the Importance of Sign Language Phonology for a Deep Neural Network

  • Javier Martinez Rodriguez, Radboud University (Netherlands)
  • Martha Larson, Radboud University (Netherlands)
  • Louis ten Bosch, Radboud University (Netherlands)

11:56 Large-scale dataset and benchmarking for hand and face detection focused on sign language

  • Alvaro Leandro Cavalcante Carneiro, São Paulo State University (Brazil)
  • Denis Henrique Pinheiro Salvadeo, São Paulo State University (Brazil)
  • Lucas Brito Silva, São Paulo State University (Brazil)

11:57 Disambiguating Signs: Deep Learning-based Gloss-level Classification for German Sign Language by Utilizing Mouth Actions

  • Dinh Nam Pham, German Research Center for Artificial Intelligence (Germany)
  • Vera Czehmann, German Research Center for Artificial Intelligence (Germany)
  • Eleftherios Avramidis, German Research Center for Artificial Intelligence (Germany)

12:00 Lunch

13:30 Efficient Learning in Spiking Neural Networks
Organized by: Alex Rast, Nigel Crook

13:30 Efficient Learning in Spiking Models

  • Alex Rast, Oxford Brookes University (UK)
  • Mario Antoine Aoun, Na (Canada)
  • Eleni Elia, Oxford Brookes University (United Kingdom)
  • Nigel Crook, Oxford Brookes University (UK)

13:50 Spiking neural networks with Hebbian plasticity for unsupervised representation learning

  • Naresh Balaji Ravichandran, KTH Royal Institute of Technology (Sweden)
  • Anders Lansner, Stockholm University and KTH Royal Institute of Technology (Sweden)
  • Pawel Herman, KTH Royal Institute of Technology (Sweden)

14:10 Functional Resonant Synaptic Clusters for Decoding Time-Structured Spike Trains

  • Nigel Crook, Oxford Brookes University (UK)
  • Alex Rast, Oxford Brookes University (UK)
  • Eleni Elia, Oxford Brookes University (United Kingdom)
  • Mario Antoine Aoun, Na (Canada)

14:30 Efficient Learning in Spiking Neural Networks - Poster spotlights
Organized by: Alex Rast, Nigel Crook

14:30 Pattern Recognition Spiking Neural Network for Classification of Chinese Characters

  • Nicola Russo, University of West London (United Kingdom)
  • Wan Yuzhong
  • Thomas Madsen
  • Konstantin Nikolic, University of West London (UK)

14:31 Energy-efficient detection of a spike sequence

  • Louis LE COEUR, Stanford University (USA)
  • Nick Riedman, Stanford University
  • Saarthak Sarup, Stanford University
  • Kwabena Boahen, Stanford University

14:32 Anomaly Detection, and Learning Algorithms

14:32 Anomaly detection in irregular image sequences for concentrated solar power plants

  • Sukanya Patra, University of Mons (Belgium)
  • Thi Khanh Hien Le, University of Mons (Belgium)
  • Souhaib Ben Taieb, University of Mons (Belgium)

14:52 Knowledge Distillation for Anomaly Detection

  • Adrian Alan Pol, Princeton University (Switzerland)
  • Ekaterina Govorkova, MIT (Switzerland)
  • Sonja Gronroos, University of Helsinki (Finland)
  • Nadezda Chernyavskaya, CERN (Switzerland)
  • Philip Harris
  • Maurizio Pierini
  • Isobel Ojalvo
  • Peter Elmer

15:12 Anomaly Detection, and Learning Algorithms - Poster spotlights

15:12 Comparative study of the synfire chain and ring attractor model for timing in the premotor nucleus in male Zebra Finches

  • Fjola Hyseni, University of Bordeaux (France)
  • Nicolas Rougier, Inria (France)
  • Arthur Leblois, CNRS (France)

15:13 Don't skip the skips: autoencoder skip connections improve latent representation discrepancy for anomaly detection

  • Anne-Sophie Collin, Université Catholique de Louvain (Belgique)
  • Cyril de Bodt, UCLouvain - ICTEAM (Belgium)
  • Dounia Mulders, UCLouvain (Belgium)
  • Christophe De Vleeschouwer, UCLouvain (Belgium)

15:14 Variants of Neural Gas for Regression Learning

  • Thomas Villmann, Mittweida University of Applied Sciences, Saxon Institute for Computational Intelligence and Machine Learning (Germany)
  • Ronny Schubert, UAS Mittweida - SICIM (Deutschland)
  • Marika Kaden, University of Applied Sciences Mittweida, Saxony Institute for Computational Intelligence and Machine Learning (Germany)

15:15 Hybrid Deep Learning-Based Air and Water Quality Prediction Model

  • Jungeun Yoon, Andong National University (Republic of Korea)
  • Dasong Yu, Andong National University (Republic of Korea)
  • youngjae lee, ETRI (South Korea)

15:16 Sleep analysis in a CLIS patient using soft-clustering: a case study

  • Sophie Adama, Department of Neuromorphic Information Processing LEIPZIG UNIVERSITY, Germany (Germany)
  • Martin Bogdan, Leipzig University (Germany)

15:17 FairBayRank: A Fair Personalized Bayesian Ranker

  • Armielle Noulapeu Ngaffo, University of Namur - NaDI - Faculty of Computer Science - PReCISE (Belgium)
  • Julien Albert, University of Namur - NaDI - Faculty of Computer Science - PReCISE (Belgium)
  • Benoit Frénay, Université de Namur (Belgium)
  • Gilles Perrouin, University of Namur - NaDI - Faculty of Computer Science - PReCISE (Belgium)

15:18 Robust and Cheap Safety Measure for Exoskeletal Learning Control with Estimated Uniform PAC (EUPAC)

  • Felix Weiske, University of Applied Sciences Leipzig (Germany)
  • Jens Jäkel, University of Applied Sciences Leipzig (Germany)

15:19 On Feature Removal for Explainability in Dynamic Environments

  • Fabian Fumagalli, CITEC - Bielefeld University (Germany)
  • Maximilian Muschalik, LMU Munich (Germany)
  • Eyke Hüllermeier, LMU Munich (Germany)
  • Barbara Hammer, CITEC - Bielefeld University (Germany)

15:20 Coffee break and poster exhibition

17:00 End of conference