European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning



ESANN
Home
Call for papers
Special sessions
Author guidelines
Submission
Program
Infos speakers
Venue
Social events
Bruges
Registration
Hotels
Committees
Sponsors
Photos
Proceedings
Past ESANN
Get a password
About


 
Login:  Password:   Password forgotten ?

20th European Symposium On Artificial Neural Networks, Computational Intelligence and Machine Learning
Bruges (Belgium), 25-26-27 April 2012

Programme

Wednesday April 25, 2012
 08h30 Registration

 09h00 Opening

 09h10 Theory and practice of adaptive input driven dynamical dystems
Organized by Peter Tino, The University of Birmingham (UK), Jochen Steil, Bielefeld University (Germany), Manjunath Gandhi, Jacobs University (Germany)
 09h10 Theory of Input Driven Dynamical Systems
 
  • Manjunath Gandhi, School of Engineering & Science - SES - Jacobs University (Germany)
  • Tino Peter, University of Birmingham (UK)
  • Herbert Jaeger, Jacobs University - School of Engineering and Science (Germany)
 09h30 Simple reservoirs with chain topology based on a single time-delay nonlinear node
 
  • José Manuel Gutiérrez, Instituto de Física de Cantabria (Spain)
  • D. San-Martín, Predicitia Intelligent Data Solutions (Spain)
  • Silvia Ortin, Instituto de Física de Cantabria (Spain)
  • Luis Pesquera, Instituto de Física de Cantabria (Spain)
 09h50 Balancing of neural contributions for multi-modal hidden state association
 
  • Christian Emmerich, CoR-Lab, Research Institute for Cognition and Robotics - Bielefeld University (Germany)
  • R. Felix Reinhart, CoR-Lab, Research Institute for Cognition and Robotics - Bielefeld University (Germany)
  • Jochen J. Steil, Research Institute for Cognition and Robotics (CoR-Lab) - Bielefeld University (Germany)
 10h10 Input-Output Hidden Markov Models for trees
 
  • Davide Bacciu, Dipartimento di Informatica - Universita' di Pisa (Italy)
  • Alessio Micheli, Dipartimento di Informatica - Universita' di Pisa (Italy)
  • Alessandro Sperduti, Dipartimento di Matematica Pura e Applicata - Universita' di Padova (Italy)

 10h30 Theory and practice of adaptive input driven dynamical dystems
Poster spotlights
 10h30 Constructive Reservoir Computation with Output Feedbacks for Structured Domains
 
  • Claudio Gallicchio, University of Pisa - Dipartimento di Informatica (Italy)
  • Alessio Micheli, Dipartimento di Informatica - Universita' di Pisa (Italy)
  • Giulio Visco, Universita` di Pisa - Dipartimento di Informatica (Italy)
 10h31 Process Mining in Non-Stationary Environments
 
  • Phil Weber, University of Birmingham (UK)
  • Tino Peter, University of Birmingham (UK)
  • Behzad Bordbar, University of Birmingham (UK)
 10h32 Short Term Memory Quantifications in Input-Driven Linear Dynamical Systems
 
  • Tino Peter, University of Birmingham (UK)
  • Ali Rodan, University of Birmingham (UK)

 10h33 Coffee break

 10h55 Regression
 10h55 Supervised learning to tune simulated annealing for in silico protein structure prediction
 
  • Alejandro Marcos Alvarez, Université de Liège - Systems and Modeling Research Unit (Belgium)
  • Francis Maes, Université de Liège - Systems and Modeling Research Unit (Belgium)
  • Louis Wehenkel, Systems and Modeling Research Unit & GIGA Research - Montefiore Institute - University of Liège (Belgium)
 11h15 Structural Risk Minimization and Rademacher Complexity for Regression
 
  • Davide Anguita, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
  • Alessandro Ghio, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
  • Luca Oneto, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
  • Sandro Ridella, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
 11h35 Quantile regression with multilayer perceptrons.
 
  • Joseph Rynkiewicz, SAMM, Université Paris 1 (France)
  • Solohaja-Faniaha Dimby, SAMM, Université Paris 1 (France)

 11h55 Regression
Poster spotlights
 11h55 Posterior regularization and attribute assessment of under-determined linear mappings
 
  • Marc Strickert, University of Siegen - Institute for Vision and Graphics (Germany)
  • Michael Seifert, Leibniz Institute of Plant Genetics and Crop Plant Research Gatersleben (Germany)
 11h56 Effects of noise-reduction on neural function approximation
 
  • Frank-Florian Steege, Ilmenau University of Technology - Neuroinformatics and Cognitive Robotics Lab (Germany)
  • Volker Stephan, Powitec Intelligent Technologies GmbH (Germany)
  • Horst-Michael Groß, Ilmenau University of Technology - Neuroinformatics and Cognitive Robotics Lab (Germany)
 11h57 Learning geometric combinations of Gaussian kernels with alternating Quasi-Newton algorithm
 
  • David Picard, ETIS - ENSEA/CNRS/Université de Cergy-Pontoise (France)
  • Nicolas Thome, LIP6 - UPMC Univ Paris 6 (France)
  • Matthieu Cord, LIP6 - UPMC Univ Paris 6 (France)
  • Alain Rakotomamonjy, LITIS EA 4108 - UFR Sciences, Dept Physics - University of Rouen (France)
 11h58 Real time drunkenness analysis in a realistic car simulation
 
  • Audrey Robinel, Laboratoire LAMIA - Université Antilles Guyane (France)
  • Didier Puzenat, Laboratoire LAMIA - Université Antilles Guyane (France)
 11h59 Learning visuo-motor coordination for pointing without depth calculation
 
  • Ananda Freire, Universidade Federal do Ceará (UFC) - Campus do Pici (Brazil)
  • Andre Lemme, CoR-Lab Research Institute for Cognition and Robotics (Germany)
  • Jochen J. Steil, Research Institute for Cognition and Robotics (CoR-Lab) - Bielefeld University (Germany)
  • Guilherme Barreto, Universidade Federal do Ceará (UFC) - Campus do Pici - Depto. de Engenharia de Teleinformática (DETI) (Brazil)

 12h00 Brain-computer interfaces
 12h00 BCI Signal Classification using a Riemannian-based kernel
 
  • Alexandre Barachant, CEA / LETI (France)
  • Stephane Bonnet, CEA / LETI (France)
  • Marco Congedo, Gipsa-lab - DIS (France)
  • Christian Jutten, Gipsa-lab - DIS (France)

 12h20 Brain-computer interfaces
Poster spotlights
 12h20 One Class SVM and Canonical Correlation Analysis increase performance in a c-VEP based Brain-Computer Interface (BCI)
 
  • Martin Spüler, Wilhelm-Schickard-Institute for Computer Science - University of Tübingen (Germany)
  • Wolfgang Rosenstiel, Wilhelm-Schickard-Institute for Computer Science - University of Tübingen (Germany)
  • Martin Bogdan, Computer Engineering - University of Leipzig (Germany)
 12h21 Automatic selection of the number of spatial filters for motor-imagery BCI
 
  • Yuan Yang, Telecom ParisTech/CNRS LTCI - Signal and Image Processing Department - Whist Lab - Institut Telecom (France)
  • Sylvain Chevallier, Université de Versailles Saint-Quentin - Laboratoire d'Ingénierie des Systèmes de Versailles (LISV) (France)
  • Joe Wiart, Orange Labs R&D SAFE/Wave - Whist Lab (France)
  • Isabelle BLOCH, Telecom ParisTech/CNRS LTCI - Signal and Image Processing Department - Whist Lab - Institut Telecom (France)
 12h22 The error-related potential and BCIs
 
  • Sandra Rousseau, Gipsa-lab - DIS (France)
  • Christian Jutten, Gipsa-lab - DIS (France)
  • Marco Congedo, Gipsa-lab - DIS (France)
 12h23 Semi-Supervised Neural Gas for Adaptive Brain-Computer Interfaces
 
  • Hannes Riechmann, CITEC Center of Excellence Cognitive Interaction Technology - Bielefeld University (Germany)
  • Andrea Finke, CITEC Center of Excellence Cognitive Interaction Technology - Bielefeld University (Germany)

 12h24 Lunch

 13h50 Image and time series analysis
 13h50 Combined scattering for rotation invariant texture analysis
 
  • Laurent Sifre, Ecole Polytechnique (Fran)
  • Stéphane Mallat, Ecole Polytechnique (France)
 14h10 Hidden Markov models for time series of counts with excess zeros
 
  • Madalina Olteanu, SAMM, Université Paris 1 (France)
  • James Ridgway, SAMM, Université Paris 1 (France)

 14h30 Image and time series analysis
Poster spotlights
 14h30 Application of Dynamic Time Warping on Kalman Filtering Framework for Abnormal ECG Filtering
 
  • Mohammad Niknazar, GIPSA-lab (UMR CNRS 5216) - University of Grenoble (France)
  • Bertrand Rivet, GIPSA-lab (UMR CNRS 5216) (France)
  • Christian Jutten, Gipsa-lab - DIS (France)
 14h31 texture classification based on symbolic data analysis
 
  • Carlos de Almeida, Federal University of Pernambuco - Center of Informatics (CIn) (Brazil)
  • Renata Souza, Federal University of Pernambuco - Center of Informatics (CIn) (Brazil)
  • Ana Lucia Candeias, Federal University of Pernambuco - Department of Cartographic Engineering (Brazil)
 14h32 Learning Object-Class Segmentation with Convolutional Neural Networks
 
  • Hannes Schulz, University Bonn - Dept. VI - Autonomous Intelligent Systems (Germany)
  • Sven Behnke, University Bonn - Dept. VI - Autonomous Intelligent Systems (Germany)
 14h33 Incremental feature building and classification for image segmentation
 
  • Guillaume Bernard, Molecular Imaging, Radiotherapy & Oncology - Université catholique de Louvain (Belgium)
  • Michel Verleysen, Université catholique de Louvain - Engineering Faculty - Electricity Department - DICE - Microelectronics laboratory (Belgium)
  • John Lee, Université catholique de Louvain - Pole of Molecular Imaging, Radiotherapy, and Oncology (Belgium)

 14h34 Interpretable models in machine learning
Organized by Paulo Lisboa, Liverpool John Moores University (UK), Alfredo Vellido, Technical University of Catalonia (Spain), José D. Martín, University of Valencia (Spain)
 14h34 Making machine learning models interpretable
 
  • Alfredo Vellido, Dept de Llenguatges i Sistemes Informàtics - Universitat Politècnica de Catalunya (Spain)
  • José D. Martín-Guerrero, university of Valencia (spain)
  • Paulo Lisboa, School of Computing and Mathematical Sciences - Department of Mathematics and Statistics - Liverpool John Moores University (United Kingdom)
 14h54 Interval coded scoring systems for survival analysis
 
  • Vanya Van Belle, Katholieke Universiteit Leuven - ESAT-SCD (Belgium)
  • Sabine Van Huffel, Katholieke Universiteit Leuven - ESAT-SCD (Belgium)
  • Johan Suykens, Katholieke Universiteit Leuven - ESAT-SCD (Belgium)
  • Stephen Boyd, Stanford University - Institute for Computational and Mathematical Engineering (USA)
 15h14 Visualizing the quality of dimensionality reduction
 
  • Bassam Mokbel, Bielefeld University (Germany)
  • Wouter Lueks, University of Nijmegen (The Netherlands)
  • Andrej Gisbrecht, Bielefeld University (Germany)
  • Michael Biehl, University of Groningen - Johann Bernoulli Institute for Mathematics and Computer Science (The Netherlands)
  • Barbara Hammer, Bielefeld University (Germany)
 15h34 Unmixing Hyperspectral Images with Fuzzy Supervised Self-Organizing Maps
 
  • Thomas Villmann, University of Applied Sciences Mittweida - Dep. of Mathematics, Natural & Computer Sciences (Germany)
  • Erzsebet Merenyi, Rice University Houston - Department of Statistics (USA (Tx))
  • William H. Farrand, Space Science Institute, Boulder, Colorado (USA (Boulder))
 15h54 Constructing similarity networks using the Fisher information metric
 
  • Héctor Ruiz, School of Computing and Mathematical Sciences - Department of Mathematics and Statistics - Liverpool John Moores University (United Kingdom)
  • Sandra Ortega, Departament de Bioquímica i Biología Molecular - Universitat Autònoma de Barcelona (Spain)
  • Ian Jarman, School of Computing and Mathematical Sciences - Liverpool John Moores University (United Kingdom)
  • José D. Martín-Guerrero, university of Valencia (spain)
  • Paulo Lisboa, School of Computing and Mathematical Sciences - Department of Mathematics and Statistics - Liverpool John Moores University (United Kingdom)

 16h14 Interpretable models in machine learning
Poster spotlights
 16h14 extended visualization method for classification trees
 
  • José M. Martínez-Martínez, University of Valencia (Spain)
  • Pablo Escandell-Montero, university of Valencia (spain)
  • Emilio Soria-Olivas, university of Valencia (Spain)
  • José D. Martín-Guerrero, university of Valencia (spain)
  • Juan Gómez-Sanchis, University of Valencia (Spain)
  • Joan Vila-Francés, university of Valencia (spain)
 16h15 Cartogram representation of the batch-SOM magnification factor
 
  • Alessandra Tosi, Dept de Llenguatges i Sistemes Informàtics - Universitat Politècnica de Catalunya (Spain)
  • Alfredo Vellido, Dept de Llenguatges i Sistemes Informàtics - Universitat Politècnica de Catalunya (Spain)
 16h16 Integration of Structural Expert Knowledge about Classes for Classification Using the Fuzzy Supervised Neural Gas
 
  • Marika Kästner, University of Applied Sciences Mittweida - Dep. of Mathematics - Computational Intelligence (Germany)
  • Wieland Hermann, Paracelsus Hospital Zwickau (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida - Dep. of Mathematics, Natural & Computer Sciences (Germany)
 16h17 Similarity networks for heterogeneous data
 
  • Lluís Belanche, Universitat Politècnica de Catalunya (Spain)
  • Jerónimo Hernández, University of the Basque Country (Spain)
 16h18 Discriminant functional gene groups identification with machine learning and prior knowledge
 
  • Grzegorz Zycinski, DISI - Department of Computer and Information Science - University of Genova (Italy)
  • Margherita Squillario, DISI - Department of Computer and Information Science - University of Genova (Italy)
  • Annalisa Barla, DISI - Department of Computer and Information Science - University of Genova (Italy)
  • Tiziana Sanavia, DEI - Information Engineering Department - University of Padova (Italy)
  • Alessandro Verri, DISI, University of Genoa (Italy)
  • Barbara Di Camillo, DEI - Information Engineering Department - University of Padova (Italy)

 16h19 Coffee break and poster preview


Thursday April 26, 2012
 09h00 Machine ensembles: theory and applications
Organized by Anibal R. Figueiras-Vidal, Universidad Carlos III de Madrid (Spain), Lior Rokach, Department of Information Systems Engineering, Ben-Gurion University of the Negev (Israel)
 09h00 An Exploration of Research Directions in Machine Ensemble Theory and Applications
 
  • Anibal Figueiras-Vidal, Universidad Carlos III de Madrid (Madrid)
  • Lior Rokach, Ben-Gurion University of the Negev (Israel)
 09h20 On the Independence of the Individual Predictions in Parallel Randomized Ensembles
 
  • Daniel Hernández-Lobato, Universidad Autónoma de Madrid (Spain)
  • Gonzalo Martínez-Muñoz, Universidad Autónoma de Madrid (Spain)
  • Alberto Suárez, Universidad Autónoma de Madrid (Spain)
 09h40 Introducing diversity among the models of multi-label classification ensemble
 
  • Lena Chekina, Ben-Gurion University of the Negev (Israel)
  • Lior Rokach, Ben-Gurion University of the Negev (Israel)
  • Bracha Shapira, Ben-Gurion University of the Negev (Israel)
 10h00 Distributed learning via Diffusion adaptation with application to ensemble learning
 
  • Zaid Towfic, University of California, Los Angeles (USA)
  • Jianshu Chen, University of California, Los Angeles (USA)
  • Ali Sayed, University of California, Los Angeles (USA)

 10h20 Machine ensembles: theory and applications
Poster spotlights
 10h20 Regularized Committee of Extreme Learning Machine for Regression Problems
 
  • Pablo Escandell-Montero, university of Valencia (spain)
  • José M. Martínez-Martínez, University of Valencia (Spain)
  • Emilio Soria-Olivas, university of Valencia (Spain)
  • Josep Guimerá-Tomás, University of Valencia (Spain)
  • Marcelino Martínez-Sober, University of Valencia (Spain)
  • Antonio J. Serrano-López, University of Valencia (Spain)
 10h21 Linear kernel combination using boosting
 
  • Alexis Lechervy, ETIS - ENSEA/Université de Cergy-Pontoise/CNRS (France)
  • Philippe-Henri Gosselin, ETIS - ENSEA/Universit´e de Cergy-Pontoise/CNRS (France)
  • Frédéric Precioso, I3S - UMR6070 - UNS CNRS (France)
 10h22 The stability of feature selection and class prediction from ensemble tree classifiers
 
  • Jérôme Paul, Université catholique de Louvain - ICTEAM / Machine Learning Group (Belgium)
  • Michel Verleysen, Université catholique de Louvain - Engineering Faculty - Electricity Department - DICE - Microelectronics laboratory (Belgium)
  • Pierre Dupont, Université catholique de Louvain - ICTEAM / Machine Learning Group (Belgium)

 10h23 Coffee break

 10h45 Bayesian and graphical models, optimization
 10h45 Sparse Nonparametric Topic Model for Transfer Learning
 
  • Ali Faisal, Helsinki Institute for Information Technology HIIT - Department of Information and Computer Science - Aalto University (Finland)
  • Jussi Gillberg, Helsinki Institute for Information Technology HIIT - Department of Information and Computer Science - Aalto University (Finland)
  • Jaakko Peltonen, Helsinki Institute for Information Technology HIIT - Department of Information and Computer Science - Aalto University (Finland)
  • Gayle Leen, deCODE genetics (Iceland)
  • Samuel Kaski, Helsinki Institute for Information Technology HIIT - Department of Information and Computer Science - Aalto University (Finland)
 11h05 Assessment of sequential Boltmann machines on a lexical processing task
 
  • Alberto Testolin, Department of Pure and Applied Mathematics - University of Padova (Italy)
  • Alessandro Sperduti, Dipartimento di Matematica Pura e Applicata - Universita' di Padova (Italy)
  • Ivilin Stoianov, University of Padova - Dipartimento di Psicologia Generale and Center for Cognitive Science (Italy)
  • Marco Zorzi, University of Padova - Dipartimento di Psicologia Generale and Center for Cognitive Science (Italy)
 11h25 Functional Mixture Discriminant Analysis with hidden process regression for curve classification
 
  • Faicel Chamroukhi, Information Sciences and Systems Lab (LSIS) - UMR CNRS 7296 - University of the South Toulon-Var (France)
  • Hervé Glotin, Information Sciences and Systems Lab (LSIS) - UMR CNRS 7296 - University of the South Toulon-Var (France)
  • Céline Rabouy, Information Sciences and Systems Lab (LSIS) - UMR CNRS 7296 - University of the South Toulon-Var (France)

 11h45 Bayesian and graphical models, optimization
Poster spotlights
 11h45 An analysis of Gaussian-binary restricted Boltzmann machines for natural images
 
  • Nan Wang, Institut für Neuroinformatik - Ruhr-Universität Bochum (Germany)
  • Jan Melchior, Institut für Neuroinformatik - Ruhr-Universität Bochum (Germany)
  • Laurenz Wiskott, Institut für Neuroinformatik - Ruhr-Universität Bochum (Germany)
 11h46 learning task relatedness via dirichlet process priors for linear regression models
 
  • Marcel Hermkes, Institute of Earth and Environmental Science - University Potsdam (Germany)
  • Nicolas Kuehn, Institute of Earth and Environmental Science - University of Potsdam (Germany)
  • Carsten Riggelsen, Institute of Earth and Environmental Science - University of Potsdam (Germany)
 11h47 EMFit based Ultrasonic Phased Arrays with evolved Weights for Biomimetic Target Localization
 
  • Jan Steckel, University of Antwerp - FTEW MTT (Belgium)
  • Andre Boen, University of Antwerp - FTEW MTT (Belgium)
  • Dieter Vanderest, University of Antwerp - FTEW MTT (Belgium)
  • Herbert Peremans, University of Antwerp - FTEW MTT (Belgium)

 11h49 Unsupervised learning
 11h48 magnitude sensitive competitive learning
 
  • Enrique Pelayo, Instituto de Investigacion en Ingeniería de Aragón - Universidad de Zaragoza (Spain)
  • David Buldain, Instituto de Investigacion en Ingeniería de Aragón - Universidad de Zaragoza (Spain)
  • Carlos Orrite, Instituto de Investigacion en Ingeniería de Aragón - Universidad de Zaragoza (Spain)
 12h08 From neuronal cost-based metrics towards sparse coded signals classification
 
  • Anthony Mouraud, CEA-LIST - Laboratoire d'Outils pour l'Analyse de Données (France)
  • Quentin Barthélemy, CEA-LIST - Laboratoire d'Outils pour l'Analyse de Données (France)
  • Aurélien Mayoue, CEA-LIST - Laboratoire d'Outils pour l'Analyse de Données (France)
  • Cédric Gouy-Pailler, CEA-LIST - Laboratoire d'Outils pour l'Analyse de Données (France)
  • Anthony Larue, CEA-LIST - Laboratoire d'Outils pour l'Analyse de Données (France)
  • Hélène Paugam-Moisy, LIRIS, CNRS (France)
 12h28 Hybrid hierarchical clustering: cluster assessment via cluster validation indices
 
  • Mark Embrechts, Rensselaer Polytechnic Institute - Dept. Industrial and Systems Engineering (USA)
  • Jonathan Linton, Telfer School of Management - University of Ottawa (Canada)
  • Christopher Gatti, Rensselaer Polytechnic Institute - Department of industrial and Systems Engineering (USA)

 12h48 Unsupervised learning
Poster spotlights
 12h48 Unsupervised learning of motion patterns
 
  • Thomas Guthier, TU Darmstadt - Control Theory and Robotics (Germany)
  • Julian Eggert, Honda Research Institute Europe (Germany)
  • Volker Willert, TU-Darmstadt - Control theory and robotics (Germany)
 12h49 Robust clustering of high-dimensional data
 
  • Anastasios Bellas, University Paris 1 - Panthéon-Sorbonne (France)
  • Charles Bouveyron, University Paris 1 - Panthéon-Sorbonne (France)
  • Marie Cottrell, University Paris 1 - Panthéon-Sorbonne (France)
  • Jérôme Lacaille, Snecma, Groupe Safran (France)
 12h50  Image reconstruction using an iterative SOM based algorithm
 
  • jouini Manel, LOCEAN (france)
  • Thiria Sylvie, LOCEAN (france)
  • crépon Michel, Locean (france)

 12h51 Lunch

 14h20 Statistical methods and kernel-based algorithms
Organized by Kris De Brabanter, Katholieke Universiteit Leuven (Belgium)
 14h20 Deconvolution in nonparametric statistics
 
  • Kris De Brabanter, Department of Electrical Engineering (ESAT) - Research Division SCD - Katholieke Universiteit Leuven (Belgium)
  • Bart De Moor, Katholieke Universiteit Leuven (Belgium)
 14h40 Weighted/Structured Total Least Squares problems and polynomial system solving
 
  • Philippe Dreesen, Katholieke Universiteit Leuven (Belgium)
  • Kim Batselier, Katholieke Universiteit Leuven (Belgium)
  • Bart De Moor, Katholieke Universiteit Leuven (Belgium)
 15h00 Joint Regression and Linear Combination of Time Series for Optimal Prediction
 
  • Dries Geebelen, K.U.Leuven, ESAT/SCD (SISTA) (Belgium)
  • Kim Batselier, Katholieke Universiteit Leuven (Belgium)
  • Philippe Dreesen, Katholieke Universiteit Leuven (Belgium)
  • Signoretto Marco, K.U.Leuven, ESAT/SCD (SISTA) (Belgium)
  • Johan Suykens, Katholieke Universiteit Leuven - ESAT-SCD (Belgium)
  • Bart De Moor, Katholieke Universiteit Leuven (Belgium)
  • Joos Vandewalle, K.U.Leuven, ESAT/SCD (SISTA) (Belgium)
 15h20 Averaging of kernel functions
 
  • Lluís Belanche, Universitat Politècnica de Catalunya (Spain)
  • Alessandra Tosi, Dept de Llenguatges i Sistemes Informàtics - Universitat Politècnica de Catalunya (Spain)

 15h40 Statistical methods and kernel-based algorithms
Poster spotlights
 15h40 maximum likelihood estimation and polynomial system solving
 
  • Kim Batselier, Katholieke Universiteit Leuven (Belgium)
  • Philippe Dreesen, Katholieke Universiteit Leuven (Belgium)
  • Bart De Moor, Katholieke Universiteit Leuven (Belgium)

 15h42 Classification and model selection
 15h41 L1-based compression of random forest models
 
  • Arnaud Joly, Systems and Modeling Research Unit & GIGA Research - University of Liège - Montefiore Institute (Belgium)
  • François Schnitzler, Systems and Modeling Research Unit & GIGA Research - Montefiore Institute - University of Liège (Belgium)
  • Pierre Geurts, Systems and Modeling Research Unit & GIGA Research - Montefiore Institute - University of Liège (Belgium)
  • Louis Wehenkel, Systems and Modeling Research Unit & GIGA Research - Montefiore Institute - University of Liège (Belgium)
 16h01 RNN Based Batch Mode Active Learning Framework
 
  • Gaurav Maheshwari, International Institute of Information Technology,Hyderabad,India (INDIA)
  • Vikram Pudi, IIIT Hyderabad (India)
 16h21 Adaptive learning for complex-valued data
 
  • Kerstin Bunte, University of Bielefeld - CITEC Center of Excellence (Germany)
  • Frank-Michael Schleif, University of Bielefeld (Germany)
  • Michael Biehl, University of Groningen - Johann Bernoulli Institute for Mathematics and Computer Science (The Netherlands)

 16h42 Classification and model selection
Poster spotlights
 16h41 Automatic Group-Outlier Detection
 
  • Amine Chaibi, Laboratoire d'Informatique de Paris-Nord (France)
  • Azzag Hanane, Laboratoire d'Informatique de Paris-Nord (France)
  • Mustapha Lebbah, Laboratoire d'Informatique de Paris-Nord (France)
 16h42 A CUSUM approach for online change-point detection on curve sequences
 
  • Nicolas CHEIFETZ, IFSTTAR - Laboratoire GRETTIA (France)
  • Allou Samé, IFSTTAR - GRETTIA (France)
  • Patrice Aknin, IFSTTAR - GRETTIA (France)
  • Emmanuel DE VERDALLE, Veolia Environnement Recherche & Innovation (France)
 16h43 One-class classifier based on extreme value statistics
 
  • David Martinez-Rego, University of A Coruña (Spain)
  • Evan Kriminger, University of Florida - CNEL Laboratory (USA)
  • Jose C. Principe, University of Florida - CNEL Laboratory (USA)
  • Oscar Fontenla-Romero, University of A Coruña - Facultade de Informatica (Spain)
  • Amparo Alonso-Betanzos, University of A Coruña - Facultade de Informatica (Spain)
 16h44 Classifying Scotch Whisky from near-infrared Raman spectra with a Radial Basis Function Network with Relevance Learning
 
  • Andreas Backhaus, Fraunhofer Institute for Factory Operation and Automation IFF (Germany)
  • Praveen Cheriyan Ashok, School of Physics & Astronomy - University of St. Andrews (United Kingdom)
  • Bavishna Balagopal Praveen, University of St. Andrews - School of Physics & Astronomy (United Kingdom)
  • Kishan Dholakia, University of St. Andrews - School of Physics & Astronomy (United Kingdom)
  • Udo Seiffert, Fraunhofer Institute for Factory Operation and Automation IFF (Germany)
 16h45 Supervised and unsupervised classification approaches for human activity recognition using body-mounted sensors
 
  • Dorra Trabelsi, LISSI Laboratory - University of Paris-Est Créteil-UPEC (France)
  • Samer Mohammed, LISSI Laboratory - University of Paris-Est Créteil-UPEC (France)
  • Faicel Chamroukhi, Information Sciences and Systems Lab (LSIS) - UMR CNRS 7296 - University of the South Toulon-Var (France)
  • Latifa Oukhellou, University Paris-Est, IFSTTAR, GRETTIA, (France)
  • Yacine Amirat, LISSI Laboratory - University of Paris-Est Créteil-UPEC (France)
 16h46 Matrix relevance LVQ in steroid metabolomics based classification of adrenal tumors
 
  • Michael Biehl, University of Groningen - Johann Bernoulli Institute for Mathematics and Computer Science (The Netherlands)
  • Petra Schneider, University of Birmingham - Centre for Endocrinology, Diabetes, and Metabolism - School of Clinical and Experimental Medicine (UK)
  • David Smith, University of Birmingham - Centre for Endocrinology, Diabetes, and Metabolism - School of Clinical and Experimental Medicine (UK)
  • Han Stiekema, University of Groningen - Johann Bernoulli Institute for Mathematics and Computer Science (The Netherlands)
  • Angela Taylor, University of Birmingham - Centre for Endocrinology, Diabetes and Metabolism - School of Clinical and Experimental Medicine (UK)
  • Beverly Hughes, University of Birmingham - Centre for Endocrinology, Diabetes, and Metabolism - School of Clinical and Experimental Medicine (UK)
  • Cedric Shackleton, University of Birmingham - Centre for Endocrinology, Diabetes, and Metabolism - School of Clinical and Experimental Medicine (UK)
  • Paul Stewart, University of Birmingham - Centre for Endocrinology, Diabetes, and Metabolism - School of Clinical and Experimental Medince (UK)
  • Wiebke Arlt, University of Birmingham - Centre for Endocrinology, Diabetes, and Metabolism - School of Clinical and Experimental Medicine (UK)
 16h47 Recognition of HIV-1 subtypes and antiretroviral drug resistance using weightless neural networks
 
  • Caio Souza, Universidade Federal do Rio de Janeiro - Instituto Alberto Luiz Coimbra de Pós Graduação e - Pesquisa de Engenharia, Programa de Engenharia de Sistemas. (Brazil)
  • Flavio Nobre, Universidade Federal do Rio de Janeiro - Instituto Alberto Luiz Coimbra de Pós Graduação e - Pesquisa em Engenharia, Programa de Engenharia Biomédica (Brazil)
  • Priscila Lima, Universidade Federal Rural do Rio de Janeiro, - Instituto de Ciências Exatas, Departamento de Matemática. (Brazil)
  • Robson Silva, Universidade Federal Rural do Rio de Janeiro, - Instituto de Ciências Exatas, Departamento de Matemática. (Brazil)
  • Rodrigo Brindeiro, Universidade Federal do Rio de Janeiro - Instituto de Biologia - Departamento de Genética (Brazil)
  • Felipe França, Universidade Federal do Rio de Janeiro - Instituto Alberto Luiz Coimbra de Pós Graduação e - Pesquisa de Engenharia, Programa de Engenharia de Sistemas. (Brazil)
 16h48 Adaptive Optimization for Cross Validation
 
  • Rudi Alessandro, Robotics, Brain and Cognitive Sciences Dept - Istituto Italiano di Tecnologia (Italy)
  • Chiusano Gabriele, DISI - University of Genoa (Italy)
  • Alessandro Verri, DISI, University of Genoa (Italy)
 16h49 The `K' in K-fold Cross Validation
 
  • Davide Anguita, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
  • Luca Ghelardoni, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
  • Alessandro Ghio, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
  • Luca Oneto, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)
  • Sandro Ridella, DIBE - Dept. of Biophysical and Electronic Engineering - University of Genova (Italy)

 16h50 Coffee break and poster preview


Friday April 27, 2012
 09h00 Recent developments in clustering algorithms
Organized by Charles Bouveyron, Université Paris 1 (France), Barbara Hammer, Bielefeld University (Germany), Thomas Villmann, University of Applied Sciences Mittweida (Germany)
 09h00 Recent developments in clustering algorithms
 
  • Charles Bouveyron, University Paris 1 - Panthéon-Sorbonne (France)
  • Barbara Hammer, Bielefeld University (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida - Dep. of Mathematics, Natural & Computer Sciences (Germany)
 09h20 Curves clustering with approximation of the density of functional random variables
 
  • Julien Jacques, Université Lille 1 - Laboratoire Paul Painlevé (FRANCE)
  • Cristian Preda, Université Lille 1 - Laboratoire Paul Painlevé (France)
 09h40 Modified Conn-Index for the evaluation of fuzzy clusterings
 
  • Tina Geweniger, University of Applied Sciences Mittweida - Computational Intelligence Group (Deutschland)
  • Marika Kästner, University of Applied Sciences Mittweida - Dep. of Mathematics - Computational Intelligence (Germany)
  • Mandy Lange, University of Applied Sciences Mittweida - Computational Intelligence Group (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida - Dep. of Mathematics, Natural & Computer Sciences (Germany)

 10h00 Recent developments in clustering algorithms
Poster spotlights
 10h00 modularity-based clustering for network-constrained trajectories
 
  • Mohamed Khalil El Mahrsi, Télécom ParisTech (France)
  • Fabrice Rossi, Université Paris I Pantheon-Sorbonne - SAMM (France)
 10h01 A Discussion on Parallelization Schemes for Stochastic Vector Quantization Algorithms
 
  • Matthieu Durut, Lokad and Telecom ParisTech - INFRES (France)
  • Benoit Patra, Lokad and Université Pierre et Marie Curie - LSTA (France)
  • Fabrice Rossi, Université Paris I Pantheon-Sorbonne - SAMM (France)
 10h02 Dissimilarity Clustering by Hierarchical Multi-Level Refinement
 
  • Brieuc Conan-Guez, Laboratoire d?Informatique Théorique et Appliquée - Université Paul Verlaine de Metz (France)
  • Fabrice Rossi, Université Paris I Pantheon-Sorbonne - SAMM (France)
 10h03 Relevance learning for time series inspection
 
  • Andrej Gisbrecht, Bielefeld University (Germany)
  • Dusan Sovilj, Aalto University (Finland)
  • Barbara Hammer, Bielefeld University (Germany)
  • Amaury Lendasse, Aalto University (Lendasse)

 10h04 Feature selection and information-based learning
 10h04 How regular is neuronal activity?
 
  • Lubomir Kostal, Institute of Physiology AS CR, v.v.i. (Czech Republic)
  • Petr Lansky, Institute of Physiology AS CR, v.v.i. (Czech Republic)
  • Ondrej Pokora, Institute of Physiology AS CR, v.v.i. (Czech Republic)
 10h24 On the Potential Inadequacy of Mutual Information for Feature Selection
 
  • Benoît Frénay, Université catholique de Louvain (Belgium)
  • Gauthier Doquire, Université catholique de Louvain (Belgium)
  • Michel Verleysen, Université catholique de Louvain - Engineering Faculty - Electricity Department - DICE - Microelectronics laboratory (Belgium)

 10h44 Feature selection and information-based learning
Poster spotlights
 10h44 Cluster homogeneity as a semi-supervised principle for feature selection using mutual information
 
  • Frederico Coelho, Universidade Federal de Minas Gerais - Programa de Pós-graduação, Escola de Engenharia (Brazil)
  • Antonio Padua Braga, Universidade Federal de Minas Gerais - Departmento de Engenharia Eletrônica, Escola de Engenharia (Brazil)
  • Michel Verleysen, Université catholique de Louvain - Engineering Faculty - Electricity Department - DICE - Microelectronics laboratory (Belgium)
 10h45 enhanced emotion recognition by feature selection to animate a talking head
 
  • Hela Daassi-Gnaba, Université Paris 8 (France)
  • Yacine OUSSAR, Laboratoire de Physique et d?Etude des Materiaux - ESPCI-ParisTech (FRANCE)
 10h46 Range-based non-orthogonal ICA using cross-entropy method
 
  • Easter Selvan Suviseshamuthu, Université catholique de Louvain, Department of Mathematical Engineering (Belgium)
  • Amit Chattopadhyay, Université catholique de Louvain, Department of Mathematical Engineering (Belgium)
  • Umberto Amato, Istituto per le Applicazioni del Calcolo 'Mauro Picone' CNR - Sede di Napoli (Italy)
  • Pierre-Antoine Absil, Université catholique de Louvain, Department of Mathematical Engineering (Belgium)

 10h47 Coffee break

 11h05 Nonlinear dimensionality reduction and topological learning
 11h05 Type 1 and 2 symmetric divergences for stochastic neighbor embedding
 
  • John Lee, Université catholique de Louvain - Pole of Molecular Imaging, Radiotherapy, and Oncology (Belgium)
 11h25 Out-of-sample kernel extensions for nonparametric dimensionality reduction
 
  • Andrej Gisbrecht, Bielefeld University (Germany)
  • Wouter Lueks, University of Nijmegen (The Netherlands)
  • Bassam Mokbel, Bielefeld University (Germany)
  • Barbara Hammer, Bielefeld University (Germany)
 11h45 A generative model that learns Betti numbers from a data set
 
  • Maxime Maillot, CEA (France)
  • Michaël Aupetit, CEA (France)
  • Gerard Govaert, UTC - Heudiasyc (France)

 12h05 Lunch

 13h30 Recurrent and neural networks, reinforcement learning, control
 13h30 Highly efficient localisation utilising weightless neural systems
 
  • Ben McElroy, Engineering and Digital Arts Department - University of Kent (Kent)
  • Gillham Michael, Engineering and Digital Arts Department - University of Kent (Kent)
  • Gareth Howells, Engineering and Digital Arts Department - University of Kent (Kent)
  • Sarah Spurgeon, Engineering and Digital Arts Department - University of Kent (Kent)
  • Kelly Michael, Engineering and Digital Arts Department - University of Kent (Kent)
  • John Batchelor, Engineering and Digital Arts Department - University of Kent (Kent)
  • Pepper Matthew, East Kent Hospitals University Foundation Trust (Kent)
 13h50 The Exploration vs Exploitation Trade-Off in Bandit Problems: An Empirical Study
 
  • Bernard Manderick, VUB (Belgium)
  • Saba Yahyaa - VUB (Belgium)

 14h10 Recurrent and neural networks, reinforcement learning, control
Poster spotlights
 14h10 intrinsic plasticity via natural gradient descent
 
  • Klaus Neumann, Research Institute for Cognition and Robotics (CoR-Lab) - Bielefeld University (Germany)
  • Jochen J. Steil, Research Institute for Cognition and Robotics (CoR-Lab) - Bielefeld University (Germany)
 14h11 Complex Valued Artificial Recurrent Neural Network as a Novel Approach to Model the Perceptual Binding Problem
 
  • Alexey Minin, Technical University of Munich - Siemens LLC (Russian Federation)
  • Alois Knoll, Technische Universitaet Muenchen - Robotics and Embedded Systems (Germany)
  • Hans-Georg Zimmermann, Siemens AG - Corporate Technology (Germany)
 14h12 A discrete/rhythmic pattern generating RNN
 
  • Tim Waegeman, Department of Electronics and Information Systems - Ghent University (Belgium)
  • Francis Wyffels, Department of Electronics and Information Systems - Ghent University (Belgium)
  • Benjamin Schrauwen, Department of Electronics and Information Systems - Ghent University (Belgium)
 14h13 Fast calibration of hand movements-based interface for arm exoskeleton control
 
  • Hugo Martin, Université de Versailles Saint-Quentin - Laboratoire d'Ingénierie des Systèmes de Versailles (France)
  • Sylvain Chevallier, Université de Versailles Saint-Quentin - Laboratoire d'Ingénierie des Systèmes de Versailles (LISV) (France)
  • Eric Monacelli, Université de Versailles Saint-Quentin - Laboratoire d'Ingénierie des Systèmes de Versailles (France)
 14h14 Manifold-based non-parametric learning of action-value functions
 
  • Hunor Jakab, Babes-Bolyai University - Faculty of Mathematics and Computer Science (Romania)
  • Lehel Csato, Babes-Bolyai University - Faculty of Mathematics and Computer Science (Romania)
 14h15 Recurrent Neural State Estimation in Domains with Long-Term Dependencies
 
  • Siegmund Duell, TU Berlin (Germany)
  • Lina Weichbrodt, Otto-von-Guericke-University Magdeburg (Germany)
  • Alexander Hans, TU Ilmenau (Germany)
  • Steffen Udluft, Siemens AG (Germany)
 14h16 Using event-based metric for event-based neural network weight adjustment
 
  • Thierry Vieville, Cortex - Inria Sophia Antipolis (France)
  • Rodrigo Salas, Universidad de Valparaiso. Departamento de Ingenieria Biomedica. Chile (Chile)
  • Bruno Cessac, Inria (France)

 14h17 Parallel hardware architectures for acceleration of neural network computation
Organized by Ulrich Rückert, Bielefeld University (Germany), Erzsébet Merényi, Rice University (USA)
 14h17 Parallel neural hardware: the time is right
 
  • Ulrich Rückert, University of Bielefeld - AG Kognitronik & Sensorik - Center of Excellence - Cognitive Interaction Technology CITEC (Germany)
  • Erzsebet Merenyi, Rice University Houston - Department of Statistics (USA (Tx))
 14h37 Towards biologically realistic multi-compartment neuron model emulation in analog VLSI
 
  • Sebastian Millner, Kirchhoff-Institut für Physik - Universität Heidelberg (Germany)
  • Andreas Hartel, Kirchhoff-Institut für Physik - Universität Heidelberg (Germany)
  • Johannes Schemmel, Kirchhoff-Institut für Physik - Universität Heidelberg (Germany)
  • Karlheinz Meier, Kirchhoff-Institut für Physik - Universität Heidelberg (Germany)

 14h57 Parallel hardware architectures for acceleration of neural network computation
Poster spotlights
 14h57 A GPU-accelerated algorithm for self-organizing maps in a distributed environment
 
  • Peter Wittek, University of Borås - Swedish School of Library and Information Science (Sweden)
  • Sándor Darányi, University of Borås - Swedish School of Library and Information Science (Sweden)
 14h58 Low-Power Manhattan Distance Calculation Circuit for Self-Organizing Neural Networks Implemented in the CMOS Technology
 
  • Rafal Dlugosz, University of Technology and Life Sciences - Faculty of Telecommunication and Electrical Engineering (Poland)
  • Tomasz Talaska, University of Technology and Life Sciences - Faculty of Telecommunication and Electrical Engineering (Poland)
  • Witold Pedrycz, University of Alberta - Department of Electrical and Computer Engineering (Canada)
  • Pierre-Andre Farine, Swiss Federal Institute of Technology in Lausanne (EPFL) - Institute of Microtechnology - Electronics and Signal Processing Laboratory (ESPLAB) (Switzerland)
 14h59 Parallelization of Deep Networks
 
  • Michele De Filippo De Grazia, University of Padova - Dipartimento di Psicologia Generale and Center for Cognitive Science (Italy)
  • Ivilin Stoianov, University of Padova - Dipartimento di Psicologia Generale and Center for Cognitive Science (Italy)
  • Marco Zorzi, University of Padova - Dipartimento di Psicologia Generale and Center for Cognitive Science (Italy)
 15h00 Hardware accelerated real time classification of hyperspectral imaging data for coffee sorting
 
  • Andreas Backhaus, Fraunhofer Institute for Factory Operation and Automation IFF (Germany)
  • Jan Lachmair, University of Bielefeld - AG Kognitronik & Sensorik - Exzellenzcluster Cognitive Interaction Technology (CITEC) (Germany)
  • Ulrich Rückert, University of Bielefeld - AG Kognitronik & Sensorik - Center of Excellence - Cognitive Interaction Technology CITEC (Germany)
  • Udo Seiffert, Fraunhofer Institute for Factory Operation and Automation IFF (Germany)
 15h01 Implementation Issues of Kohonen Self-Organizing Map Realized on FPGA
 
  • Rafal Dlugosz, University of Technology and Life Sciences - Faculty of Telecommunication and Electrical Engineering (Poland)
  • Marta Kolasa, University of Technology and Life Sciences - Faculty of Telecommunication and Electrical Engineering (Poland)
  • Michal Szulc, Poznan University of Technology - Chair of Computer Engineering (Poland)
  • Witold Pedrycz, University of Alberta - Department of Electrical and Computer Engineering (Canada)
  • Pierre-Andre Farine, Swiss Federal Institute of Technology in Lausanne (EPFL) - Institute of Microtechnology - Electronics and Signal Processing Laboratory (ESPLAB) (Switzerland)
 15h02 A hybrid CMOS/memristive nanoelectronic circuit for programming synaptic weights
 
  • Arne Heittmann, Chair of Electrical Engineering and Computer Systems - RWTH Aachen University (Germany)
  • Tobias G. Noll, Chair of Electrical Engineering and Computer Systems - RWTH Aachen University (Germany)
 15h03 gNBXe -- a Reconfigurable Neuroprocessor for Various Types of Self-Organizing Maps
 
  • Jan Lachmair, University of Bielefeld - AG Kognitronik & Sensorik - Exzellenzcluster Cognitive Interaction Technology (CITEC) (Germany)
  • Erzsebet Merenyi, Rice University Houston - Department of Statistics (USA (Tx))
  • Mario Porrmann, Heinz Nixdorf Institute - University of Paderborn - System and Circuit Technology (Germany)
  • Ulrich Rückert, University of Bielefeld - AG Kognitronik & Sensorik - Center of Excellence - Cognitive Interaction Technology CITEC (Germany)

 15h04 Coffee break and poster preview

 17h00 End of conference



 

 

 


 


For any information: Michel Verleysen - esann@uclouvain.be