ESANN 2020 programme

Friday 2 October 2020

09:00 Opening

09:10 Adversarial learning, robustness and fairness

09:10 Attacking Model Sets with Adversarial Examples

• István Megyeri, University of Szeged (Hungary)
• István Hegedűs, University of Szeged (Hungary)
• Mark Jelasity, University of Szeged (Hungary)

09:30 GraN: An Efficient Gradient-Norm Based Detector for Adversarial and Misclassified Examples

• Julia Lust, Robert Bosch GmbH (Germany)
• Alexandru Paul Condurache, Robert Bosch GmbH (Germany)

09:50 Unsupervised Latent Space Translation Network

• Magda Friedjungová, Faculty of Information Technology, Czech Technical University in Prague (Czech Republic)
• Daniel Vašata, Faculty of Information Technology, Czech Technical University in Prague (Czech Republic)
• Tomáš Chobola, Faculty of Information Technology, Czech Technical University in Prague (Czech Republic)
• Marcel Jiřina, Faculty of Information Technology, Czech Technical University in Prague (Czech Republic)

10:10 Efficient computation of counterfactual explanations of LVQ models

• André Artelt, CITEC - Bielefeld University (Germany)
• Barbara Hammer, CITEC - Bielefeld University (Germany)

10:30 MultiMBNN: Matched and Balanced Causal Inference with Neural Networks

• Ankit Sharma, Tata Consultancy Services (India)
• Garima Gupta, Tata Consultancy Services (India)
• Ranjitha Prasad, Indraprastha Institute of Information Technology, Delhi (India)
• Arnab Chatterjee, Tata Consultancy Services (India)
• Lovekesh Vig, Tata Consultancy Services (India)
• Gautam Shroff, Tata Consultancy Services (India)

10:50 Learning Deep Fair Graph Neural Networks

• Luca Oneto, University of Genoa (Italy)
• Nicolò Navarin, University of Padua (Italy)
• Michele Donini, Amazon (United States)

11:10 Adversarial learning, robustness and fairness - poster spotlights

11:10 Interpretation of Model Agnostic Classifiers via Local Mental Images

• Aluizio Lima Filho, UFRJ - Universidade Federal do Rio de Janeiro / PESC / COPPE (Brasil)
• Gabriel Guarisa, UFRJ - Universidade Federal do Rio de Janeiro / PESC / COPPE (Brasil)
• Leopoldo Lusquino, UFRJ - Universidade Federal do Rio de Janeiro / PESC / COPPE (Brasil)
• Luiz Oliveira, UFRJ - Universidade Federal do Rio de Janeiro / PESC / COPPE (Brasil)
• Carlos Cosenza, UFRJ - Universidade Federal do Rio de Janeiro / PEP / COPPE (Brasil)
• Felipe França, Universidade Federal do Rio de Janeiro (Brazil)
• Priscila Lima, Universidade Federal do Rio de Janeiro (Brazil)

11:11 Estimating Individual Treatment Effects through Causal Populations Identification

• Celine Beji, Paris-Dauphine University (France)
• Eric Benhamou, Lamsade (France)
• Michael Bon
• Florian Yger, Université Paris-Dauphine, PSL Research University, CNRS, LAMSADE (France)
• Jamal Atif

11:12 Towards Adversarial Attack Resistant Deep Neural Networks

• Tiago Alves, State University of Rio de Janeiro (Brazil)
• Sandip Kundu, University of Massachusetts (United States)

11:13 Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models

• Pawel Morawiecki, Institute of Computer Science, Polish Academy of Sciences (Poland)
• Przemysław Spurek
• Marek Śmieja, Jagiellonian University (Poland)
• Jacek Tabor

11:14 Adversarial domain adaptation without gradient reversal layer

• Aymen Cherif, Eura Nova (Belgium)
• Hugo Serieys, EURA NOVA (France)

11:15 Coffee break

11:35 Image and signal processing, matrix computations and topological data

11:35 ASAP - A Sub-sampling Approach for Preserving Topological Structures

• Abolfazl Taghribi, University of Groningen (Netherlands)
• Kerstin Bunte, University of Groningen (Netherlands)
• Michele Mastropietro, Ghent University (Universiteit Gent) (Belgium)
• Sven De Rijcke, Ghent University (Universiteit Gent) (Belgium)
• Peter Tino, University of Birmingham (United Kingdom)

11:55 Image completion via nonnegative matrix factorization using B-splines

• Cécile Hautecoeur, UCLouvain (Belgique)
• François Glineur, UCLouvain (Belgique)

12:15 Motion Segmentation using Frequency Domain Transformer Networks

• Hafez Farazi, University of Bonn (Germany)
• Sven Behnke, University of Bonn (Germany)

12:35 Image and signal processing, matrix computations and topological data - poster spotlights

12:35 Predicting low gamma- from lower frequency band activity in electrocorticography

• Marc Van Hulle, KU Leuven (België)
• Bob Van Dyck, KU Leuven (België)
• Wittevrongel Benjamin, KU Leuven (Belgium)
• Flavio Camarrone, KU Leuven (Belgium)
• Ine Dauwe, Ghent University Hospital (Belgium)
• Evelien Carrette, Ghent University Hospital (Belgium)
• Alfred Meurs, Ghent University Hospital (Belgium)
• Paul Boon, Ghent University Hospital (Belgium)
• Dirk Van Roost, Ghent University Hospital

12:36 Lower bounds on the nonnegative rank using a nested polytopes formulation

• Julien Dewez, UCLouvain (Belgium)
• François Glineur, UCLouvain (Belgique)

12:37 Lunch

13:45 Virtual visit of Bruges

14:00 Deep learning and graph neural networks

14:00 Resume: A Robust Framework for Professional Profile Learning & Evaluation

• Clara Gainon de Forsan de Gabriac, LIP6, Sorbonne Université. (France)
• Constance Scherer, LIP6, Sorbonne Université. (France)
• Amina Djelloul, LIP6, Sorbonne Université. (France)
• Vincent Guigue, LIP6, Sorbonne Université. (France)
• Patrick Gallinari, LIP6, Sorbonne Université. (France)

14:20 Invariant Integration in Deep Convolutional Feature Space

• Matthias Rath, Robert Bosch GmbH (Germany)
• Alexandru Paul Condurache, Robert Bosch GmbH (Germany)

14:40 On Learning a Control System without Continuous Feedback

• Georgi Angelov, Sofia University (Bulgaria)
• Bogdan Georgiev, Fraunhofer IAIS (Germany)

15:00 Time Series Prediction using Disentangled Latent Factors

• Perrine Cribier-Delande, Sorbonne Université, CNRS, LIP6, F-75005 Paris, France (France)
• Raphaël Puget, Renault (France)
• Vincent Guigue, LIP6, Sorbonne Université. (France)
• Ludovic Denoyer, LIP6, Sorbonne Université. (France)

15:20 Biochemical Pathway Robustness Prediction with Graph Neural Networks

• Marco Podda, Università di Pisa (Italy)
• Alessio Micheli, Università di Pisa (Italy)
• Davide Bacciu, Università di Pisa (Italy)
• Paolo Milazzo, Università di Pisa (Italy)

15:40 Graph Neural Networks for the Prediction of Protein-Protein Interfaces

• Niccolò Pancino, SAILAB - University of Siena, DINFO - University of Florence (Italy)
• Alberto Rossi, University of Florence, Department of Information Engineering (Italy)
• Giorgio Ciano, SAILAB - University of Siena, DINFO - University of Florence (Italy)
• Giorgia Giacomini, SAILAB - University of Siena (Italy)
• Simone Bonechi, SAILAB - University of Siena (Italy)
• Paolo Andreini, SAILAB - University of Siena (Italy)
• Franco Scarselli, SAILAB - University of Siena (Italy)
• Monica Bianchini, SAILAB - University of Siena (Italy)
• Pietro Bongini, SAILAB - University of Siena, DINFO - University of Florence (Italy)

16:00 Deep learning and graph neural networks - poster spotights

16:00 Embedding of FRPN in CNN architecture

• Alberto Rossi, University of Florence, Department of Information Engineering (Italy)
• Markus Hagenbuchner, University of Wollongong - School of Computing and Information Technology (Australia)
• Franco Scarselli, SAILAB - University of Siena (Italy)
• Ah Chung Tsoi, University of Wollongong - School of Computing and Information Technology (Australia)

16:01 Verifying Deep Learning-based Decisions for Facial Expression Recognition

• Ines Rieger, Fraunhofer Institute for Integrated Circuits IIS (Germany)
• Rene Kollmann, University of Bamberg (Germany)
• Bettina Finzel, University of Bamberg (Germany)
• Dominik Seuss, Fraunhofer Institute for Integrated Systems IIS (Germany)
• Ute Schmid, University of Bamberg (Germany)

16:02 Cost-free resolution enhancement in Convolutional Neural Networks for medical image segmentation

• Oscar J. Pellicer Valero, Intelligent Data Analysis Laboratory, Department of Electronic Engineering, ETSE (Engineering School), Universitat de València (UV) (Spain)
• María J. Rupérez-Moreno, Centro de Investigación en Ingeniería Mecánica (CIIM), Universitat Politècnica de València (UPV) (Spain)
• José D. Martín-Guerrero, Universitat de València (Spain)

16:03 Linear Graph Convolutional Networks

• Nicolò Navarin, University of Padua (Italy)
• Wolfgang Erb, University of Padua (Italy)
• Luca Pasa, University of Padova, Italy (Italy)
• Alessandro Sperduti, University of Padua (Italy)

16:04 Deep Recurrent Graph Neural Networks

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

16:05 Investigating 3D-STDenseNet for Explainable Spatial Temporal Crime Forecasting

• Brian Maguire, Innovation Exchange, IBM Ireland (Ireland)
• Faisal Ghaffar, IBM Ireland Ltd. (Ireland)

16:06 Visualization of the Feature Space of Neural Networks

• Carlos M. Alaíz, Universidad Autónoma de Madrid (Spain)
• Ángela Fernández, Universidad Autónoma de Madrid (Spain)
• José R. Dorronsoro, Universidad Autónoma de Madrid (Spain)

16:07 Theoretically Expressive and Edge-aware Graph Learning

• Federico Errica, Università di Pisa (Italy)
• Davide Bacciu, Università di Pisa (Italy)
• Alessio Micheli, Università di Pisa (Italy)

16:08 Random Signal Cut for Improving Multimodal CNN Robustness of 2D Road Object Detection

• Robin Condat, LITIS - INSA Rouen Normandie (France)
• Alexandrina Rogozan, LITIS - INSA Rouen Normandie (France)
• Abdelaziz Bensrhair, LITIS - INSA Rouen Normandie (France)

16:09 New Results on Sparse Autoencoders for Posture Classification and Segmentation

• Doreen Jirak, University of Hamburg (Hamburg)
• Stefan Wermter, University of Hamburg , Department of Informatics (Germany)

16:10 Fréchet Mean Computation in Graph Space through Projected Block Gradient Descent

• Nicolas Boria, Université Paris-Dauphine, PSL Research University, CNRS, LAMSADE (France)
• Benjamin Negrevergne, Université Paris-Dauphine, PSL Research University, CNRS, LAMSADE (France)
• Florian Yger, Université Paris-Dauphine, PSL Research University, CNRS, LAMSADE (France)

16:11 Improving Light-weight Convolutional Neural Networks for Face Recognition Targeting Resource Constrained Platforms

• Iulian-Ionut Felea, PhD. Student at University "Politehnica" of Bucharest, Romania (Romania)
• Radu Dogaru, University “Politehnica” of Bucharest School Dept. of Applied Electronics and Information Engineering (Romania)

16:12 Variational MIxture of Normalizing Flows

• Guilherme Pires, Instituto Superior Técnico - Departamento de Engenharia Electrotécnica e de Computadores (Portugal)
• Mário Figueiredo, Instituto de Telecomunicações, Instituto Superior Técnico, Universidade de Lisboa, Portugal (Portugal)

16:13 Fast Deep Neural Networks Convergence using a Weightless Neural Model

• Alan T. L. Bacellar, Federal University of Rio de Janeiro (UFRJ) (Brasil)
• Brunno F. Goldstein, Federal University of Rio de Janeiro (UFRJ) (Brazil)
• Victor C Ferreira, Federal University of Rio de Janeiro (UFRJ) (Brazil)
• Leandro Santiago, Federal University of Rio de Janeiro (UFRJ) (Brazil)
• Priscila Lima, Universidade Federal do Rio de Janeiro (Brazil)
• Felipe França, Universidade Federal do Rio de Janeiro (Brazil)

16:14 An Empirical Study of Iterative Knowledge Distillation for Neural Network Compression

• Sharan Yalburgi, BITS Pilani, K.K. Birla Goa Campus (India)
• Tirtharaj Dash, BITS Pilani, K.K. Birla Goa Campus (India)
• Ramya Hebbalaguppe, TCS Research (India)
• Srinidhi Hegde, TCS Research (India)
• Ashwin Srinivasan, BITS Pilani, K.K. Birla Goa Campus (India)

16:15 Why state-of-the-art deep learning barely works as good as a linear classifier in extreme multi-label text classification

• Mohammadreza Qaraei, Aalto University (Finland)
• Sujay Khandagale, Columbia University (USA)
• Rohit Babbar, Aalto University (Finland)

16:16 Incorporating Human Priors into Deep Reinforcement Learning for Robotic Control

• Manon Flageat, Imperial College London (UK)
• Kai Arulkumaran, Imperial College London (UK)
• Anil A Bharath, Imperial College London (UK)

16:17 Sparse K-means for mixed data via group-sparse clustering

• Marie Chavent, INRIA Bordeaux
• Jérôme Lacaille, Datalab, Safran Aircraft Engines (France)
• Alex Mourer, SAMM, Université Paris 1 (France)
• Madalina Olteanu, SAMM, Université Paris 1 Panthéon Sorbonne (France)

16:18 Machine Learning Applied to Computer Networks - organized by Alexander Gepperth (University of Applied Sciences Fulda, Germany), Sebastian Rieger (University of Applied Sciences Fulda, Deutschland)
Organized by: Alexander Gepperth, Sebastian Rieger

16:18 A Survey of Machine Learning applied to Computer Networks

• Alexander Gepperth, University of Applied Sciences Fulda (Germany)
• Sebastian Rieger, University of Applied Sciences Fulda (Deutschland)

16:38 Machine Learning Applied to Computer Networks - poster spotlights
Organized by: Alexander Gepperth, Sebastian Rieger

16:38 Anomaly Detection Approach in Cyber Security for User and Entity Behavior Analytics System

• Vladimir Muliukha, Peter the Great St.Petersburg Polytechnic University (Russia)
• Alexey Lukashin, Peter the Great St.Petersburg Polytechnic University (Russia)
• Lev Utkin, Peter the Great St.Petersburg Polytechnic University (Russia)
• Mikhail Popov, Peter the Great St.Petersburg Polytechnic University (Russia)
• Anna Meldo, Peter the Great St.Petersburg Polytechnic University (Russia)

16:39 Poster discussion session

18:15 End of first day

 

Saturday 3 October 2020

09:00 Quantum Machine Learning - Organized by José D. Martín-Guerrero (Universitat de València, Spain), Lucas Lamata (Universidad de Sevilla, Spain)
Organized by: José D. Martín-Guerrero, Lucas Lamata

09:00 Quantum Machine Learning

• José D. Martín-Guerrero, Universitat de València (Spain)
• Lucas Lamata, Universidad de Sevilla (Spain)

09:20 Machine learning framework for control in classical and quantum domains

• Archismita Dalal, University of Calgary (Canada)
• Eduardo J. P\'aez, University of Calgary
• Seyed Shakib Vedaie, University of Calgary
• Barry C. Sanders, University of Calgary

09:40 Understanding and improving unsupervised training of Boltzman machines

• Przemys{\l}aw Grzybowski, Faculty of Physics, Adam Mickiewicz University, Umultowska 85, 61-614 Pozna{\'n}, Poland (Polska)
• Gorka Muñoz-Gil, ICFO (Spain)
• Alejandro Pozas-Kerstjens, Universidad Complutense de Madrid (Spain)
• Miguel Angel Garcia-March
• Maciej Lewenstein, ICFO (Spain)

10:00 Quantum-Inspired Learning Vector Quantization for Classification Learning

• Thomas Villmann, University of Applied Sciences Mittweida, Saxony Institute for Computational Intelligence and Machine Learning (Deutschland)
• Jensun Ravichandran, University of Applied Sciences Mittweida, Saxony Institute for Computational Intelligence and Machine Learning (Germany)
• Alexander Engelsberger, University of Applied Sciences Mittweida, Saxony Institute for Computational Intelligence and Machine Learning (Germany)
• Andrea Villmann, Berufliches Schulzentrum Döbeln-Mittweida (Germany)
• Marika Kaden, University of Applied Sciences Mittweida, Saxony Institute for Computational Intelligence and Machine Learning (Germany)

10:20 An quantum algorithm for feedforward neural networks tested on existing quantum hardware

• Daniele Bajoni, Dipartimento di Ingegneria Industriale e dell'Informazione Universita di Pavia (Italy)
• Dario Gerace, University of Pavia (Italy)
• Chiara Macchiavello
• Francesco Tacchino, University of Pavia (Italy)
• Panagiotis Barkoutsos
• Ivano Tavernelli

10:40 Quantum Machine Learning - poster spotlights
Organized by: José D. Martín-Guerrero, Lucas Lamata

10:41 Approximating Archetypal Analysis Using Quantum Annealing

• Sebastian Feld, LMU Munich (Germany)
• Christoph Roch, LMU Munich (Germany)
• Katja Geirhos, LMU Munich (Germany)
• Thomas Gabor, LMU Munich (Deutschland)

10:42 Explorations in Quantum Neural Networks with Intermediate Measurements

• Lukas Franken, Fraunhofer IAIS (Germany)
• Bogdan Georgiev, Fraunhofer IAIS (Germany)

10:43 Coffee break

11:25 Recurrent networks and reinforcement learning

11:25 A Distributed Neural Network Architecture for Robust Non-Linear Spatio-Temporal Prediction

• Matthias Karlbauer, University of Tübingen (Germany)
• Sebastian Otte, University of Tübingen (Germany)
• Hendrik Lensch, University of Tübingen (Germany)
• Thomas Scholten, University of Tübingen (Germany)
• Volker Wulfmeyer, University of Hohenheim (Germany)
• Martin Butz, University of Tübingen (Germany)

11:45 Softmax Recurrent Unit: A new type of RNN cell

• Lucas Vos, Open University (The Netherlands)
• Twan van Laarhoven, Radboud University (The Netherlands)

12:05 Language Grounded Task-Adaptation in Reinforcement Learning

• Matthias Hutsebaut-Buysse, University of Antwerp - IDLab - imec (Belgium)
• Kevin Mets, University of Antwerp - IDLab - imec (Belgium)
• Steven Latré, University of Antwerp (Belgium)

12:25 Recurrent networks and reinforcement learning - poster spotlights

12:26 Object-centered Fourier Motion Estimation and Segment-Transformation Prediction

• moritz wolter, University of Bonn (Germany)
• Angela Yao, National University of Singapore (Singapore)
• Sven Behnke, University of Bonn (Germany)

12:27 Recurrent Feedback Improves Recognition of Partially Occluded Objects

• Markus Roland Ernst, Frankfurt Institute for Advanced Studies and Goethe-Universität Frankfurt (Germany)
• Jochen Triesch, Frankfurt Institute for Advanced Studies and Goethe-Universität Frankfurt (Germany)
• Thomas Burwick, Frankfurt Institute for Advanced Studies and Goethe-Universität Frankfurt (Germany)

12:28 Sequence Classification using Ensembles of Recurrent Generative Expert Modules

• Marius Hobbhahn, University of Tübingen (Germany)
• Martin Butz, University of Tübingen (Germany)
• Sarah Fabi, University of Tuebingen - Neuro-Cognitive Modeling Group (Germany)
• Sebastian Otte, University of Tübingen (Germany)

12:29 Epistemic Risk-Sensitive Reinforcement Learning

• Hannes Eriksson, Chalmers University of Technology (Sweden)
• Christos Dimitrakakis, Informatics Institute (Norway)

12:30 Tournament Selection Improves Cartesian Genetic Programming for Atari Games

• Tim Cofala, University of Oldenburg (Germany)
• Lars Elend, University of Oldenburg (Germany)
• Oliver Kramer, University of Oldenburg (Germany)

12:31 Handling missing data in recurrent neural networks for air quality forecasting

• Michel Tokic, Siemens AG / Corporate Technology (Germany)
• Anja von Beuningen, Siemens AG / Corporate Technology (Germany)
• Christoph Tietz, Siemens AG / Corporate Technology (Germany)
• Hans-Georg Zimmermann, Fraunhofer IIS (Germany)

12:32 Unsupervised learning - poster spotlights

12:32 Self-organizing maps in manifolds with complex topologies: An application to the planning of closed path for indoor UAV patrols

• Hervé Frezza-Buet, CentraleSupélec (France)

12:33 Detection of abnormal driving situations using distributed representations and unsupervised learning

• Florian Mirus, BMW AG (Germany)
• Terrence C. Stewart, Applied Brain Research Inc. (Canada)
• Jörg Conradt, KTH Royal Institute of Technology (Sweden)

12:34 Comparison of Cluster Validity Indices and Decision Rules for Different Degrees of Cluster Separation

• Sara Kaczynska, Université catholique de Louvain (Belgium)
• Rebecca Marion, Université catholique de Louvain (Belgium)
• Rainer von Sachs, Université catholique de Louvain (Belgium)

12:35 Lunch

14:00 Feature selection and dimensionality reduction

14:00 Sparse Metric Learning in Prototype-based Classification

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

14:20 Joint optimization of predictive performance and selection stability

• Victor Hamer, UCLouvain (Belgium)
• Pierre Dupont, UCLouvain (Belgium)

14:40 Perplexity-free Parametric t-SNE

• Francesco Crecchi, Università di Pisa (Italy)
• Cyril de Bodt, Université catholique de Louvain (Belgium)
• Michel Verleysen, UCLouvain - ICTEAM institute (Belgium)
• Lee John, UCLouvain (Belgium)
• Davide Bacciu, Università di Pisa (Italy)

15:00 Feature selection and dimensionality reduction - poster spotlights

15:00 Explaining t-SNE Embeddings Locally by Adapting LIME

• Adrien Bibal, University of Namur (Belgium)
• Viet Minh VU, NADI Institute - PReCISE Research Center, University of Namur (Belgium)
• Géraldin Nanfack, University of Namur (Belgium)
• Benoit Frénay, Université de Namur (Belgium)

15:01 Do we need hundreds of classifiers or a good feature selection?

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

15:02 Random Projection in supervised non-stationary environments

• Moritz Heusinger, University of Applied Sciences Würzburg-Schweinfurt (Germany)
• Frank-Michael Schleif, University of Applied Sciences Würzburg-Schweinfurt (Germany)

15:03 On Feature Selection Using Anisotropic General Regression Neural Network

• Federico Amato, University of Lausanne - Faculty of Geosciences and Environment, IDYST (Switzerland)
• Fabian Guignard, University of Lausanne - Institute of Earth Surface Dynamics (IDYST) (Switzerland)
• Philippe Jacquet, Scientific Computing and Research Support Unit, Computer Center (Switzerland)
• Mikhail Kanevski, University of Lausanne - Institute of Earth Surface Dynamics (IDYST) (Switzerland)

15:04 Statistical learning and optimization

15:04 A preconditioned accelerated stochastic gradient descent algorithm

• Alexandru Onose, ASML Netherlands B.V. (The Netherlands)
• Seyed Iman Mossavat, asml (netherlands)
• Henk-Jan H. Smilde, ASML Netherlands B.V. (The Netherlands)

15:24 Improving the Union Bound: a Distribution Dependent Approach

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

15:44 Compressive Learning of Generative Networks

• Vincent Schellekens, ICTEAM/UCLouvain (Belgium)
• Laurent Jacques, ICTEAM/UCLouvain (Belgium)

16:04 Statistical learning and optimization - poster spotlights

16:04 Learning Step Size Adaptation in Evolution Strategies

• Oliver Kramer, University of Oldenburg (Germany)

16:06 Tensor Decompositions in Deep Learning - organized by Davide Bacciu (Università di Pisa, Italy), Danilo Mandic (Imperial College, United Kingdom)
Organized by: Davide Bacciu, Danilo Mandic

16:06 Tensor Decompositions in Deep Learning

• Davide Bacciu, Università di Pisa (Italy)
• Danilo Mandic, Imperial College (United Kingdom)

16:26 Tensor Decompositions in Recursive Neural Networks for Tree-Structured Data

• Daniele Castellana, Università di Pisa (Italy)
• Davide Bacciu, Università di Pisa (Italy)

16:46 Tensor Decompositions in Deep Learning - poster spotlights
Organized by: Davide Bacciu, Danilo Mandic

16:46 Mining Temporal Changes in Strengths and Weaknesses of Cricket Players Using Tensor Decomposition

• Swarup Ranjan Behera, Indian Institute of Technology Guwahati (India)
• Vijaya Saradhi, Indian Institute of Technology Guwahati (India)

16:47 Image and text analysis - poster spotlights

16:47 3D U-Net for Segmentation of Plant Root MRI Images in Super-Resolution

• Yi Zhao, University of Bonn, Computer Science Institute VI, Autonomous Intelligent Systems (Germany)
• Nils Wandel, University of Bonn, Computer Science Institute VI, Autonomous Intelligent Systems (Germany)
• Magdalena Landl, Forschungszentrum Jülich GmbH, Institute of Bio- and Geosciences, IBG-3 (Germany)
• Andrea Schnepf, Forschungszentrum Jülich GmbH, Institute of Bio- and Geosciences, IBG-3 (Germany)
• Sven Behnke, University of Bonn (Germany)

16:48 Respiratory Pattern Recognition from Low-Resolution Thermal Imaging

• Salla Aario, Aalto University (Finland)
• Ajinkya Gorad, Aalto University (Finland)
• Miika Arvonen, Kuopio University Hospital (Finland)
• Simo Sarkka, Aalto University (Finland)

16:49 Missing Image Data Imputation using Variational Autoencoders with Weighted Loss

• Ricardo Cardoso Pereira, Centre for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
• Joana Cristo Santos, Centre for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
• José Pereira Amorim, Centre for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)
• Pedro Pereira Rodrigues, Center for Health Technology and Services Research (CINTESIS) - University of Porto (Portugal)
• Pedro Henriques Abreu, Centre for Informatics and Systems of the University of Coimbra (CISUC) (Portugal)

16:50 Seq-to-NSeq model for multi-summary generation

• Guillaume Le Berre, University of Lorraine (LORIA) (France)
• Christophe Cerisara, University of Lorraine (LORIA) (France)

16:51 CNN Encoder to Reduce the Dimensionality of Data Image for Motion Planning

• Janderson Ferreira, University of Pernambuco (Brazil)
• Agostinho Junior, Universidade de Pernambuco - Escola Politécnica de Pernambuco (Brazil)
• Yves Mendes Galvao, University of Pernambuco (Brazil)
• Bruno Fernandes, Universidade de Pernambuco - Escola Politécnica de Pernambuco (Brazil)
• Pablo Barros, Italian Institute of Technology (Italy)

16:52 Poster discussion session

18:30 End of second day

18:30 Virtual visit of the Halve Maan brewery

 

Sunday 4 October 2020

09:00 Learning from partially labeled data - organized by Siamak Mehrkanoon (Maastricht University, The Netherlands), Xiaolin Huang (Shanghai Jiao Tong University, China), Johan Suykens (KU Leuven, Belgium)
Organized by: Siamak Mehrkanoon, Xiaolin Huang, Johan Suykens

09:00 Learning from partially labeled data

• Siamak Mehrkanoon, Maastricht University (The Netherlands)
• Xiaolin Huang, Shanghai Jiao Tong University (China)
• Johan Suykens, KU Leuven (Belgium)

09:20 Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks

• Bernardo Pérez Orozco, University of Oxford (United Kingdom)
• Stephen J Roberts, University of Oxford (United Kingdom)

09:40 Domain Invariant Representations with Deep Spectral Alignment

• Christoph Raab, University of Applied Science Würzburg-Schweinfurt (Germany)
• Peter Meier, University of Applied Science Würzburg-Schweinfurt (Germany)
• Frank-Michael Schleif, University of Applied Sciences Würzburg-Schweinfurt (Germany)

10:00 Learning from partially labeled data - poster spotlights
Organized by: Siamak Mehrkanoon, Xiaolin Huang, Johan Suykens

10:00 Weighted Emprirical Risk Minimization: Transfer Learning based on Importance Sampling

• Robin Vogel, Télécom Paris / IDEMIA (France)
• Mastane Achab, Télécom Paris (France)
• Stéphan Clémençon, Telecom Paris (France)
• Charles Tillier, Télécom Paris (France)

10:01 Modelling human sound localization with deep neural networks.

• Kiki van der Heijden, Maastricht University (Netherlands)
• Siamak Mehrkanoon, Maastricht University (The Netherlands)

10:02 A Real-time PCB Defect Detector Based on Supervised and Semi-supervised Learning

• FAN HE, SHANGHAI JIAO TONG UNIVERSITY (CHINA)
• Sanli Tang, Hikvision Research Institute (China)
• Siamak Mehrkanoon, Maastricht University (The Netherlands)
• Xiaolin Huang, Shanghai Jiao Tong University (China)
• Jie Yang, Shanghai Jiao Tong University (China)

10:03 Machine learning in the pharmaceutical industry - organized by Paul Smyth (GlaxoSmithKline Tech Data & Analytics, Belgium), Thibault Helleputte (DNAlytics, Belgium), Gael de Lannoy (GlaxoSmithKline, CMC Statistical Sciences, Belgium)
Organized by: Paul Smyth, Thibault Helleputte, Gael de Lannoy

10:03 Machine learning in the biopharma industry

• Gael de Lannoy, GlaxoSmithKline, CMC Statistical Sciences (Belgium)
• Thibault Helleputte, DNAlytics (Belgium)
• Paul Smyth, GlaxoSmithKline Tech Data & Analytics (Belgium)

10:23 Deep Learning to Detect Bacterial Colonies for the Production of Vaccines

• Paul Smyth, GlaxoSmithKline Tech Data & Analytics (Belgium)
• Lee John, UCLouvain (Belgium)
• Gael de Lannoy, GlaxoSmithKline, CMC Statistical Sciences (Belgium)
• Thomas Beznik, RELU (Belgium)

10:43 Machine learning in the pharmaceutical industry - poster spotlights
Organized by: Paul Smyth, Thibault Helleputte, Gael de Lannoy

10:43 A Systematic Assessment of Deep Learning Models for Molecule Generation

• Davide Rigoni, University of Padua (Italy)
• Nicolò Navarin, University of Padua (Italy)
• Alessandro Sperduti, University of Padua (Italy)

10:44 An agile machine learning project in pharma - developing a Mask R-CNN-based web application for bacterial colony counting

• Paul Smyth, GlaxoSmithKline Tech Data & Analytics (Belgium)
• Tanguy Naets, Radix.ai (Belgium)
• Gael de Lannoy, GlaxoSmithKline, CMC Statistical Sciences (Belgium)
• Laurent Sorber, Radix.ai (Belgium)

10:45 Coffee break

11:05 Frontiers in Reservoir Computing - organized by Claudio Gallicchio (University of Pisa, Italy), Mantas Lukoševičius (Kaunas University of Technology, Lithuania), Simone Scardapane (Sapienza University of Rome, Italia)
Organized by: Claudio Gallicchio, Mantas Lukoševičius, Simone Scardapane

11:05 Frontiers in Reservoir Computing

• Claudio Gallicchio, University of Pisa (Italy)
• Mantas Lukoševičius, Kaunas University of Technology (Lithuania)
• Simone Scardapane, Sapienza University of Rome (Italia)

11:25 Reservoir memory machines

• Benjamin Paassen, Bielefeld University (Germany)
• Alexander Schulz, Bielefeld University (Germany)

11:45 Pyramidal Graph Echo State Networks

• Filippo Maria Bianchi, NORCE - the Norwegian Research Center (Norway)
• Claudio Gallicchio, University of Pisa (Italy)
• Alessio Micheli, Università di Pisa (Italy)

12:05 Frontiers in Reservoir Computing - poster spotlights
Organized by: Claudio Gallicchio, Mantas Lukoševičius, Simone Scardapane

12:05 Simplifying Deep Reservoir Architectures

• Claudio Gallicchio, University of Pisa (Italy)
• Alessio Micheli, Università di Pisa (Italy)
• Antonio Sisbarra, University of Pisa (Italy)

12:06 Self-organized dynamic attractors in recurrent neural networks

• Benedikt Vettelschoss, Institute for cross-disciplinary physics and complex systems (IFISC), University of the Balearic Islands (Spain)
• Matthias Freiberger, Ghent University - imec - IDLab (Belgium)
• Joni Dambre, Ghent University - imec - IDLab (Belgium)

12:07 Self-Organizing Kernel-based Convolutional Echo State Network for Human Actions Recognition

• Gin Chong Lee, Multimedia University Faculty of Engineering and Technology (Malaysia)
• Chu Kiong Loo, University of Malaya, Department of Artificial Intelligence, Faculty of Computer Science and Information Technology (Malaysia)
• Wei Shiung Liew, University of Malaya (Malaysia)
• Stefan Wermter, University of Hamburg , Department of Informatics (Germany)

12:08 Lunch

13:40 Language processing in the era of deep learning - organized by Ivano Lauriola (University of Padova, Italy), Alberto Lavelli (Fondazione Bruno Kessler, Italy), Fabio Aiolli (University of Padova, Italy)
Organized by: Ivano Lauriola, Alberto Lavelli, Fabio Aiolli

13:40 Language processing in the era of deep learning

• Ivano Lauriola, University of Padova (Italy)
• Alberto Lavelli, Fondazione Bruno Kessler (Italy)
• Fabio Aiolli, University of Padova (Italy)

14:00 Modular Length Control for Sentence Generation

• Katya Kudashkina, University of Guelph (Canada)
• Peter Wittek, University of Toronto
• Jamie Kiros, Google
• Graham W. Taylor, University of Guelph

14:20 Entity-Pair Embeddings for Improving Relation Extraction in the Biomedical Domain

• Farrokh Mehryary, Department of Future Technologies, TurkuNLP Group, University of Turku, Turku, Finland (Finland)
• Hans Moen, Department of Future Technologies, Turku NLP Group, University of Turku, Turku, Finland (Finland)
• Tapio Salakoski, Department of Future Technologies, Faculty of Science and Engineering, University of Turku, Turku, Finland (Finland)
• Filip Ginter, Department of Future Technologies, Turku NLP Group, University of Turku, Turku, Finland (Finland)

14:40 Adversarials-1 in Speech Recognition: Detection and Defence

• Nils Worzyk, University Oldenburg (Germany)
• Stefan Niewerth, Carl-von-Ossietzky Universität Oldenburg (Germany)
• Oliver Kramer, University Oldenburg (Germany)

15:00 Language processing in the era of deep learning - poster spotlights
Organized by: Ivano Lauriola, Alberto Lavelli, Fabio Aiolli

15:00 On the long-term learning ability of LSTM LMs

• Wim Boes, KU Leuven (Belgium)
• Robbe Van Rompaey, KU Leuven (Belgium)
• Lyan Verwimp, Apple Inc. (Belgium)
• Joris Pelemans, Apple Inc.
• Hugo Van hamme, KU Leuven (Belgium)
• Patrick Wambacq, KU Leuven (Belgium)

15:01 Cross-Encoded Meta Embedding towards Transfer Learning

• György Kovács, EISLAB Machine Learning, Luleå University of Technology (Sweden)
• Rickard Brännvall, RISE SICS North, RISE Research Institutes of Sweden (Sweden)
• Johan Öhman, Experimental Mechanics, Luleå University of Technology (Sweden)
• Marcus Liwicki, EISLAB Machine Learning, Luleå University of Technology (Sweden)

15:02 Exploring the feature space of character-level embeddings

• Ivano Lauriola, University of Padova (Italy)
• Stefano Campese, Omnys srl (italy)
• Alberto Lavelli, Fondazione Bruno Kessler (Italy)
• Fabio Rinaldi, Fondazione Bruno Kessler
• Fabio Aiolli, University of Padova (Italy)

15:03 Supervised learning - poster spotlights

15:03 Detection of elementary particles with the WiSARD n-tuple classifier

• Pedro Xavier, Universidade Federal do Rio de Janeiro (Brazil)
• Massimo De Gregorio, CNR (Italy)
• Felipe França, Universidade Federal do Rio de Janeiro (Brazil)
• Priscila Lima, Universidade Federal do Rio de Janeiro (Brazil)

15:04 Automatic Pain Intensity Recognition: Training Set Selection based on Outliers and Centroids

• Peter Bellmann, Ulm University (Germany)
• Patrick Thiam, Ulm University (Germany)
• Friedhelm Schwenker, Ulm University (Germany)

15:05 Binary and Multi-label Defect Classification of Printed Circuit Board based on Transfer Learning

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

15:06 SDOstream: Low-Density Models for Streaming Outlier Detection

• Alexander Hartl, TU Wien (Austria)
• Félix Iglesias, TU Wien (Austria)
• Tanja Zseby, TU Wien (Austria)

15:07 Locally Adaptive Nearest Neighbors

• Jan Philip Göpfert, Bielefeld University (Germany)
• Heiko Wersing, Honda Research Institute Europe (Germany)
• Barbara Hammer, CITEC - Bielefeld University (Germany)

15:08 Equilibrium Propagation for Complete Directed Neural Networks

• Matilde Tristany Farinha, INESC-ID (Portugal)
• Sérgio Pequito, Department of Industrial and Systems Engineering, Rensselaer Polytechnic Institute, Troy (NY), USA (United States of America)
• Pedro A. Santos, Department of Mathematics, Instituto Superior Técnico, Universidade de Lisboa, Portugal (Portugal)
• Mário Figueiredo, Instituto de Telecomunicações, Instituto Superior Técnico, Universidade de Lisboa, Portugal (Portugal)

15:09 On-edge adaptive acoustic models: an application to acoustic person presence detection

• Lode Vuegen, KU Leuven Campus Geel (Belgium)
• Peter Karsmakers, KU Leuven Campus Geel (Belgium)

15:10 Gaussian process regression for the estimation of stable univariate time-series processes

• Georgios Birpoutsoukis, Université catholique de Louvain (Belgium)
• Julien M. Hendrickx, Université catholique de Louvain (Belgium)

15:11 Problem Transformation Methods with Distance-Based Learning for Multi-Target Regression

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

15:12 Adapting Random Forests to Cope with Heavily Censored Datasets in Survival Analysis

• Tossapol Pomsuwan, University of Kent (United Kingdom)
• Alex Freitas, University of Kent (United Kingdom)

15:13 Model Variance for Extreme Learning Machine

• Fabian Guignard, University of Lausanne - Institute of Earth Surface Dynamics (IDYST) (Switzerland)
• Mohamed Laib, Luxembourg Institute for Science and Technology (LIST) - IT for Innovative Services (Luxembourg)
• Mikhail Kanevski, University of Lausanne - Institute of Earth Surface Dynamics (IDYST) (Switzerland)

15:14 Multi-Directional Laplacian Pyramids for Completion of Missing Data Entries

• Neta Rabin, Tel-Aviv University (Israel)

15:15 Navigational Freespace Detection for Autonomous Driving in Fixed Routes

• aparajit narayan, academy of robotics (united kingdom)
• elio tuci, University of Namur (Belgium)
• william sachiti, academy of robotics (united kingdom)
• aaron parsons, academy of robotics (united kingdom)

15:16 Similarities between policy gradient methods in reinforcement and supervised learning

• Eric Benhamou, LAMSADE Dauphine AI Square Connect (France)
• David Saltiel, AI Square Connect (France)

15:17 Best student paper award & closing remarks

15:25 Poster discussion session

16:45 End of conference