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 ?

16th European Symposium On Artificial Neural Networks
Advances in Computational Intelligence and Learning
Bruges (Belgium), 23-24-25 April 2008

Programme


Wednesday April 23, 2008
 08h30 Registration

 09h00 Opening

 09h10 Dynamical and recurrent systems, control
 09h10 Pruning and Regularisation in Reservoir Computing: a First Insight
 
  • Xavier Dutoit, Katholieke Universiteit Leuven (Belgium)
  • Benjamin Schrauwen, Ghent University (Belgium)
  • Jan Van Campenhout, Universiteit Gent (Belgium)
  • Dirk Stroobandt, Universiteit Gent (Belgium)
  • Hendrik Van Brussel, Katholieke Universiteit Leuven (Belgium)
  • Marnix Nuttin, katholieke Universiteit Leuven (Belgium)
 09h30 Design of Oscillatory Recurrent Neural Network Controllers with Gradient based Algorithms
 
  • Guillaume Jouffroy, Artificial Intelligence laboratory - University Paris 8 (France)
 09h50 Learning Inverse Dynamics: a Comparison
 
  • Duy Nguyen Tuong, Max Planck Institute of Biological Cybernetics (Germany)
  • Jan Peters, Max Planck Institute of Biological Cybernetics (Germany)
  • Matthias Seeger, Max Planck Institute of Biological Cybernetics (Germany)
  • Bernhard Schoelkopf, Max Planck Institute of Biological Cybernetics (Germany)
 10h10 Model-Based Reinforcement Learning with Continuous States and Actions
 
  • Marc Deisenroth, University of Cambridge - Department of Engineering - Computational and Biological Learning Lab (UK)
  • Carl Edward Rasmussen, Department of Engineering - Universitz of Cambridge (UK)
  • Jan Peters, Max Planck Institute for Biological Cybernetics (Germany)

 10h30 Coffee break

 10h50 Feature selection, imputation and projection
 10h50 Using the Delta Test for Variable Selection
 
  • Emil Eirola, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Elia Liitiäinen, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Amaury Lendasse, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Francesco Corona, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Michel Verleysen, Université catholique de Louvain - Machine Learning Group - DICE (Belgium)
 11h10 Metric adaptation for supervised attribute rating
 
  • Marc Strickert, Data Inspection Group - Leibniz Institute of Plant Genetics and Crop Plant Research (Germany)
  • Frank-Michael Schleif, AG Computational Intelligence - University of Leipzig (Germany)
  • Thomas Villmann, University of Leipzig - Clinic for Psychotherapy (Germany)
 11h30 K-nearest neighbours based on mutual information for incomplete data classification
 
  • Pedro J. García-Laencina, Universidad Politécnica de Cartagena - Dpto. TIC (Spain)
  • José-Luis Sancho-Gómez, Universidad Politécnica de Cartagena - Dpto. TIC (Spain)
  • Aníbal R. Figueiras-Vídal, University Carlos III de MAdrid - Dpt. of Signal Processing and Communication (Spain)
  • Michel Verleysen, Université catholique de Louvain - Machine Learning Group - DICE (Belgium)
 11h50 Nonlinear data projection on a sphere with controlled trade-off between trustworthiness and continuity
 
  • Victor Onclinx, Université catholique de Louvain - Applied Mathematics Department (Belgium)
  • Vincent Wertz, Université catholique de Louvain - Applied Mathematics Department (Belgium)
  • Michel Verleysen, Université catholique de Louvain - Machine Learning Group - DICE (Belgium)
 12h10 Rank-based quality assessment of nonlinear dimensionality reduction
 
  • John Lee, Université catholique de Louvain - Imagerie moléculaire et radiothérapie expérimentale - Machine Learning Group (Belgium)
  • Michel Verleysen, Université catholique de Louvain - Machine Learning Group - DICE (Belgium)

 12h30 Lunch

 14h00 Machine learning methods in cancer research
Organized by A. Vellido (Polytechnic Univ. Catalonia, Spain), P.J.G.Lisboa (Liverpool John Moores Univ., UK)
 14h00 Machine learning in cancer research: implications for personalised medicine
 
  • Alfredo Vellido, Universitat Politècnica de Catalunya (UPC) (Spain)
  • Elia Biganzoli, Fondazione IRCCS Istituto Nazionale dei Tumori - Struttura de Statistica e Biometria (Italy)
  • Paulo J.G. Lisboa, School of Computing and Mathematical Sciences - Liverpool John Moores University (United Kingdom)
 14h20 Multi-class classification of ovarian tumors
 
  • Ben Van Calster, Department of Electrical Engineering (ESAT-SISTA) - Katholieke Universiteit Leuven (Belgium)
  • Dirk Timmerman, Department of Obstetrics and Gynaecology - University Hospitals Leuven (Belgium)
  • Antonia C. Testa, Istituto di Clinica Ostetrica e Ginecologica - Universita Cattolica del Sacro Cuore (Italy)
  • Lil Valentin, Department of Obstetrics and Gynaecology (Sweden)
  • Sabine Van Huffel, Department of Electrical Engineering (ESAT-SISTA) - Katholieke Universiteit Leuven (Belgium)
 14h40 A new method of DNA probes selection and its use with multi-objective neural network for predicting the outcome of breast cancer preoperative chemotherapy
 
  • René Natowicz, Université Paris-Est, ESIEE-Paris (France)
  • Antônio Braga, Universidade Federal de Minas Gerais - Departamento de Engenharia Eletrônica (Brazil)
  • Roberto Incitti, Institut Mondor de Médecine Moléculaire - Plate-forme génomique (France)
  • Euler Horta, Universidade Federal de Minas Gerais - Departamento de Engenharia Eletrônica (Brazil)
  • Roman Rouzier, Hôpital Tenon - Service de gynécologie (France)
  • Thiago Rodrigues, Universidade Federal de Lavras - Departamento de Ciência da Computação (Brazil)
  • Marcelo Costa, Universidade Federal de Minas Gerais - Departamento de Estatística, ICEx (Brazil)
 15h00 Feature Selection in Proton Magnetic Resonance Spectroscopy for Brain Tumor Classification
 
  • Félix Fernando González Navarro, Universitat Politécnica de Catalunya (Spain)
  • Luis Antonio Belanche Muñoz, Universitat Politécnica de Catalunya (Spain)
 15h20 A method for robust variable selection with significance assessment
 
  • Annalisa Barla, DISI - Universita' degli Studi di Genova (Italy)
  • Sofia Mosci, DISI - Universita' degli Studi di Genova - DIFI - Universita' degli Studi di Genova (Italy)
  • Lorenzo Rosasco, DISI - Universita' degli Studi di Genova (Italy)
  • Alessandro Verri, DISI - Universita' degli Studi di Genova (Italy)
 15h40 Survival SVM: a practical scalable algorithm
 
  • Vanya Van Belle, Katholieke Universiteit Leuven - Department of electrical engineering (ESAT), SCD (Belgium)
  • Kristiaan Pelckmans, Katholieke Universiteit Leuven - Department of electrical engineering (ESAT), SCD (Belgium)
  • Johan Suykens, Katholieke Universiteit Leuven - Department of electrical engineering (ESAT), SCD (Belgium)
  • Sabine Van Huffel, Department of Electrical Engineering (ESAT-SISTA) - Katholieke Universiteit Leuven (Belgium)

 16h00 Machine learning methods in cancer research
Poster spotlights
 16h00 DSS-oriented exploration of a multi-centre magnetic resonance spectroscopy brain tumour dataset through visualization
 
  • Enrique Romero, Universitat Politécnica de Catalunya (UPC) (Spain)
  • Margarida Julià-Sapé, Universitat Autonoma de Barcelona (UAB) (Spain)
  • Alfredo Vellido, Universitat Politècnica de Catalunya (UPC) (Spain)
 16h01 Handling almost-deterministic relationships in constraint-based Bayesian network discovery : Application to cancer risk factor identification
 
  • Sergio Rodrigues de Morais, Université de Lyon (France)
  • Alexandre Aussem, Université de Lyon, LIESP, UCBL (France)
  • Marilys Corbex, International Agency for Research on Cancer (France)

 16h02 Poster spotlights
 16h02 Using graph-theoretic measures to predict the performance of associative memory models
 
  • Lee Calcraft, University of Hertfordshire (UK)
  • Rod Adams, University of Hertfodshire (UK)
  • Weiliang Chen, University of Hertfordshire (UK)
  • Neil Davey, University of hertfordshire (UK)
 16h03 A novel autoassociative memory on the complex hypercubic lattice
 
  • Rama Murthy Garimella, International Institute of Information Technology, Hyderabad (India)
  • Praveen Dasigi, International Institute of Information Technology, Hyderabad (India)
 16h04 Word recognition and incremental learning based on neural associative memories and hidden Markov models
 
  • Zoehre Kara Kayikci, Institute for Neural Information Processing (Germany)
  • Günther Palm, Department of Neural Information Processing - University of Ulm (Germany)
 16h05 Conditional prediction of time series using spiral recurrent neural network
 
  • Huaien Gao, Database and Information Systems - University of Munich (Germany)
  • Rudolf Sollacher, Siemens AG, Corporate Technology (Germany)
 16h06 Learning to play Tetris applying reinforcement learning methods
 
  • Alexander Gross, University of Ulm - Department of Neural Information Processing (Germany)
  • Jan Friedland, University of Ulm - Institute of Neural Information Processing (Germany)
  • Friedhelm Schwenker, University of Ulm (Germany)
 16h07 QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games
 
  • Benoît Frénay, Université catholique de Louvain (Belgium)
  • Marco Saerens, Université catholique de Louvain (Belgium)
 16h08 Safe exploration for reinforcement learning
 
  • Alexander Hans, Technical University of Ilmenau - Department of Neuroinformatics (Germany)
  • Daniel Schneegass, Siemens AG, Corporate Technology - Information & Communications, Learning Systems (Germany)
  • Anton Maximilian Schäfer, University of Osnabrueck - Neuroinformatics Group (Germany)
  • Steffen Udluft, Siemens AG, Corporate Technology - Information & Communications, Learning Systems (Germany)
 16h09 Similarities and differences between policy gradient methods and evolution strategies
 
  • Verena Heidrich-Meisner, Insitut für Neuroinformatik - Ruhr-Universität Bochum (Germany)
  • Christian Igel, Institut für Neuroinformatik - Ruhr-Universität Bochum (Germany)
 16h10 Improvement in Game Agent Control Using State-Action Value Scaling
 
  • Leo Galway, University of Ulster (UK)
  • Darryl Charles, University of Ulster (UK)
  • Michaela Black, University of Ulster (UK)
 16h11 Multilayer Perceptrons with Radial Basis Functions as Value Functions in Reinforcement Learning
 
  • Victor Uc Cetina, Humboldt-Universität zu Berlin - Institut für Informatik (Germany)
 16h12 Selection of important input variables for RBF network using partial derivatives
 
  • Jarkko Tikka, Helsinki University of Technology - Department of Information and Computer Science (Finland)
  • Jaakko Hollmén, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
 16h13 A multiple testing procedure for input variable selection in neural networks
 
  • Michele La Rocca, Department of Economics and Statistics - University of Salerno (Italy)
  • Cira Perna, Department of Economics and Statistics - University of Salerno (Italy)
 16h15 Computationally Efficient Neural Field Dynamics
 
  • Alexander Gepperth, Honda Research Institute Europe GmbH (Germany)
  • Jannik Fritsch, Honda Research Institute Europe GmbH (Germany)
  • Christian Goerick, Honda Research Institute Europe GmbH (Germany)

 16h20 Coffee break and poster preview


Thursday April 24, 2008
 09h00 Biological systems and biologically-inspired networks
 09h00 The gamma cycle and its role in the formation of assemblies
 
  • Thomas Burwick, Frankfurt Institute for Advanced Studies (FIAS) - Johann Wolfgang Goethe Universität (Germany)
 09h20 The impact of axon wiring costs on small neuronal networks
 
  • Conrad Attard, University of Hertfordshire - School of Computer Science (United Kingdom)
  • Andreas Albrecht, University of Hertfordshire - Science & Technology Research Institute (UK)
 09h40 An FPGA-based model suitable for evolution and development of spiking neural networks
 
  • Hooman Shayani, Department of Computer Science - UCL (UK)
  • Peter J. Bentley, Department of Computer Science - UCL (UK)
  • Andrew M. Tyrrell, The Department of Electronics - The University of York (UK)

 10h00 Coffee break

 10h20 Clustering and vector quantization
 10h20 Self-Organizing Maps for cyclic and unbounded graphs
 
  • Markus Hagenbuchner, University of Wollongong (Australia)
  • Alessandro Sperduti, University of Padova (Italy)
  • Ah Chung Tsoi, Hong Kong Baptist University (Hong Kong)
 10h40 Clustering of Self-Organizing Map
 
  • Hanane Azzag, LIPN-UMR 7030 - Université Paris 13 - CNRS (France)
  • Mustapha Lebbah, Université Paris 13, UFR (SMBH) - LIM&BIO Lab (France)
 11h00 Explaining Ant-Based Clustering on the basis of Self-Organizing Maps
 
  • Lutz Herrmann, University of Marburg (Germany)
  • Alfred Ultsch, University of Marburg (Germany)
 11h20 Phase transitions in Vector Quantization
 
  • Aree Witoelar, Mathematics and Computing Science - University of Groningen (The Netherlands)
  • Anarta Ghosh, Nordic Bioscience (Denmark)
  • Michael Biehl, University of Groningen - Mathematics and Computing Science (The Netherlands)
 11h40 Parallelizing single patch pass clustering
 
  • Nikolai Alex, University of Applied Science Braunschweig/Wolfenbuettel (Germany)
  • Barbara Hammer, Clausthal University of Technology (Germany)
 12h00 Learning Data Representations with Sparse Coding Neural Gas
 
  • Kai Labusch, Institute for Neuro- and Bioinformatics - University of Lübeck (Germany)
  • Erhardt Barth, Institute for Neuro- and Bioinformatics - University of Lübeck (Germany)
  • Thomas Martinetz, Institute for Neuro- and Bioinformatics - University of Lübeck (Germany)

 12h20 Lunch

 13h50 Methodology and standards for data analysis with machine learning tools
Organized by D. François (Univ. cat. Louvain, Belgium)
 13h50 Methodology and standards for data analysis with machine learning tools
 
  • Damien François, Université catholique de Louvain - Machine Learning Group - INMA (Belgium)
 14h10 A Methodology for Building Regression Models using Extreme Learning Machine: OP-ELM
 
  • Yoan Miché, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Patrick Bas, Gipsa-lab UMR 5216, CNRS, INPG, UJF (France)
  • Christian Jutten, Gipsa-lab UMR 5216, CNRS, INPG, UJF (France)
  • Olli Simula, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Amaury Lendasse, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
 14h30 Do we need experts for time series forecasting?
 
  • Christiane Lemke, Bournemouth University - School of Design, Engineering and Computing (UK)
  • Bogdan Gabrys, Bournemouth University - School of Design, Engineering and Computing (UK)
 14h50 Homogeneous bipartition based on multidimensional ranking
 
  • Michael Aupetit, CEA DAM - Dept Analyse Surveillance Environnement (FRANCE)
 15h10 Feature selection on process fault detection and visualization
 
  • Tuomas Alhonnoro, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Miki Sirola, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
 15h30 Classification of chestnuts with feature selection by noise resilient classifiers
 
  • Elena Roglia, Department of computer science - University of Torino (Italy)
  • Rossella Cancelliere, Department of computer science - University of Torino (Italy)
  • Rosa Meo, Department of computer science - University of Torino (Italy)

 15h50 Methodology and standards for data analysis with machine learning tools
Poster spotlights
 15h50 GeoKernels: modeling of spatial data on geomanifolds
 
  • Alexei Pozdnoukhov, Institute of Geomatics and Analysis of Risk - University of Lausanne (Switzerland)
  • Mikhail Kanevski, Institute of Geomatics and Analysis of Risk - University of Lausanne (Switzerland)

 15h51 Poster spotlights
 15h51 Constructing ensembles of classifiers using linear projections based on misclassified instances
 
  • César García-Osorio, University of Burgos (Spain)
  • Nicolás García-Pedrajas, University of Córdoba (Spain)
 15h52 A Regularized Learning Method for Neural Networks Based on Sensitivity Analysis
 
  • Bertha Guijarro-Berdiñas, University of A Coruña (Spain)
  • Oscar Fontenla-Romero, Department of Computer Science - University of A Coruña (Spain)
  • Beatriz Perez-Sanchez, University of A Coruña (Spain)
  • Amparo Alonso-Betanzos, Department of Computer Science - University of A Coruña (Spain)
 15h53 A Method for Time Series Prediction using a Combination of Linear Models
 
  • David Martínez-Rego, Laboratory for Research and Development in Artificial Intelligence (LIDIA) - Department of Computer Science - University of A Coruña (Spain)
  • Oscar Fontenla-Romero, Department of Computer Science - University of A Coruña (Spain)
  • Amparo Alonso-Betanzos, Department of Computer Science - University of A Coruña (Spain)
 15h54 Interpretable ensembles of local models for safety-related applications
 
  • Sebastian Nusser, Siemens AG - Corporate Technology - CT IC 4 - Learning Systems (Germany)
  • Clemens Otte, Siemens AG - Corporate Technology - CT IC 4 - Learning Systems (Germany)
  • Werner Hauptmann, Siemens AG - Corporate Technology - CT IC 4 - Learning Systems (Germany)
 15h55 Multi-View Forests of Tree-Structured Radial Basis Function Networks Based on Dempster-Shafer Evidence Theory
 
  • Mohamed Farouk Abdel Hady, Institute of Neural Information Processing - University of Ulm (Germany)
  • Günther Palm, Department of Neural Information Processing - University of Ulm (Germany)
  • Friedhelm Schwenker, Institute of Neural Information Processing - University of Ulm (Germany)
 15h56 SOM based clustering with instance-level constraints
 
  • Fazia Bellal, Université de Lyon, LIESP, UCBL (France)
  • Khalid Benabdeslem, Université de Lyon, LIESP, UCBL (France)
  • Alexandre Aussem, Université de Lyon, LIESP, UCBL (France)
 15h57 Robust object segmentation by adaptive metrics in Generalized LVQ
 
  • Alexander Denecke, University of Bielefeld - Faculty of Technology - Neuroinformatics Group (Germany)
  • Heiko Wersing, Honda Research Institute Europe (Germany)
  • Jochen J. Steil, University of Bielefeld - Faculty of Technology - Neuroinformatics Group (Germany)
  • Edgar Koerner, Honda Research Institute Europe (Germany)
 15h58 Magnification Control in Relational Neural Gas
 
  • Alexander Hasenfuss, Clausthal University of Technology - Department of Informatics (Germany)
  • Barbara Hammer, Clausthal University of Technology (Germany)
  • Tina Geweniger, University of Leipzig - Clinic for Psychotherapy (Germany)
  • Thomas Villmann, University of Leipzig - Clinic for Psychotherapy (Germany)
 15h59 Parallel asynchronous neighborhood mechanism for WTM Kohonen network implemented in CMOS technology
 
  • Marta Kolasa, University of Technology and Life Sciences - Institute of Electrical Engineering (Poland)
  • Rafal Dlugosz, University of Neuchatel - Institute of Microtechnology (Switzerland)
 16h00 Initialization mechanism in Kohonen neural network implemented in CMOS technology
 
  • Tomasz Talaska, University of Technology and Life Sciences - Institute of Telecommunication (Poland)
  • Rafal Dlugosz, University of Neuchatel - Institute of Microtechnology (Switzerland)
 16h01 Neural network hardware architecture for pattern recognition in the HESS2 project
 
  • Narayanan Ramanan, IIT Madras- Dept. of Electrical Engineering (India)
  • Sonia Khatchadourian, ETIS - UMR 8051 (France)
  • Jean-Christophe Prévotet, ETIS - UMR 8051 (France)
  • Lounis Kessal, ETIS - UMR 8051 (France)
 16h02 Active and reactive use of virtual neural sensors
 
  • Massimo De Gregorio, Istituto di Cibernetica "Eduardo Caianiello" - CNR (Italy)
 16h03 Noise influence on correlated activities in a modular neuronal network: from synapses to functional connectivity
 
  • Carlo Casarino, Dipartimento di Fisica e Tecnologie Relative - Università di Palermo (Italy)
  • Gaetano Aiello, Dipartimento di Fisica e Tecnologie Relative - Università di Palermo (Italy)
  • Davide Valenti, Dipartimento di Fisica e Tecnologie Relative - Università di Palermo (Italy)
  • Bernardo Spagnolo, Dipartimento di Fisica e Tecnologie Relative - Università di Palermo (Italy)
 16h04 Neuromimetic motion indicator for visual perception
 
  • Claudio Castellanos Sánchez, Centre for Research and Advanced Studies - Laboratory of Information Technologies - Cinvestav - Tamaulipas (Mexico)

 16h05 Coffee break and poster preview


Friday April 25, 2008
 09h00 Neural Networks for Computational Neuroscience
Organized by D. Meunier, H. Paugam-Moisy (LIRIS-CNRS, France)
 09h00 Neural networks for computational neuroscience
 
  • David Meunier, Brain Mapping Unit - University of Cambridge (United Kingdom)
  • Helene Paugam-Moisy, LIRIS, UMR CNRS 5205 (France)
 09h20 Emergence of stimulus-specific synchronous response through STDP in recurrent neural networks
 
  • Frédéric Henry, Laboratoire Mouvement et Perception, UMR6152 - Faculté des sciences du sport - Université de la Méditerrannée (France)
  • Emmanuel Daucé, Laboratoire Mouvement et Perception, UMR6152 - Faculté des sciences du sport - Université de la Méditerrannée (France)
 09h40 Visual focus with spiking neurons
 
  • Sylvain Chevallier, LIMSI-CNRS - UPR 3251 (France)
  • Philippe Tarroux, LIMSI-CNRS - UPR 3251 (France)
 10h00 Simulation of a recurrent neurointerface with sparse electrical connections
 
  • Andreas Herzog, Otto-von-Guericke University Magdeburg, IESK (Germany)
  • Karsten Kube, Otto-von-Guericke University Magdeburg, IESK (Germany)
  • Bernd Michaelis, Otto-von-Guericke University Magdeburg, IESK (Germany)
  • Ana D. de Lima, Otto-von-Guericke-University Magdeburg (Germany)
  • Thomas Voigt, Otto-von-Guericke-University Magdeburg (Germany)

 10h20 Neural Networks for Computational Neuroscience
Poster spotlights
 10h20 Direct and inverse solution for a stimulus adaptation problem using SVR
 
  • Dominik Brugger, Eberhard-Karls Universität Tübingen - Wilhelm-Schickard Institut für Informatik - Technische Informatik (Germany)
  • Sergejus Butovas, Hertie-Institut für klinische Hirnforschung (Germany)
  • Martin Bogdan, Eberhard-Karls Universität Tübingen - Wilhelm-Schickard Institut für Informatik - Technische Informatik (Germany)
  • Cornelius Schwarz, Hertie-Institut für klinische Hirnforschung (Germany)
  • Wolfgang Rosenstiel, Eberhard-Karls Universität Tübingen - Wilhelm-Schickard Institut für Informatik - Technische Informatik (Germany)
 10h21 Computational model for amygdala neural networks
 
  • Jean Marc Salotti, Laboratoire Cognition et Facteurs Humains - Institut de Cognitique, Universite de Bordeaux (France)

 10h22 Coffee break

 10h45 Kernel methods
 10h45 Factored sequence kernels
 
  • Pierre Mahé, Xerox Research Center Europe (France)
  • Nicola Cancedda, Xerox Research Center Europe (France)
 11h05 Regularization path for Ranking SVM
 
  • Karina Zapien, LITIS, INSA de Rouen (France)
  • Thomas Gaertner, Fraunhofer IAIS (Germany)
  • Gilles Gasso, LITIS, INSA de Rouen (France)
  • Stéphane Canu, LITIS, INSA de Rouen (France)
 11h25 An accelerated MDM algorithm for SVM training
 
  • Alvaro Barbero, Instituto de Ingeniería del Conocimiento y - Departamento de Ingeniería Informática - Universidad Autónoma de Madrid (Spain)
  • Jorge López, Instituto de Ingeniería del Conocimiento y - Departamento de Ingeniería Informática - Universidad Autónoma de Madrid (Spain)
  • José Dorronsoro, Instituto de Ingeniería del Conocimiento y - Departamento de Ingeniería Informática - Universidad Autónoma de Madrid (Spain)
 11h45 Approximation of Gaussian process regression models after training
 
  • Thorsten Suttorp, Lehrstuhl Theoretische Biologie - Ruhr-Universität Bochum (Germany)
  • Christian Igel, Institut für Neuroinformatik - Ruhr-Universität Bochum (Germany)

 12h05 Lunch

 13h45 Machine Learning Approaches and Pattern Recognition for Spectral Data
Organized by T. Villmann (Univ. Leipzig, Germany), E. Merényi (Rice Univ., USA), U. Seiffert (IPK Gatersleben, Germany)
 13h45 Machine learning approches and pattern recognition for spectral data
 
  • Thomas Villmann, University of Leipzig - Clinic for Psychotherapy (Germany)
  • Erzsébet Merényi, Rice University (TX)
  • Udo Seiffert, Leibniz Institute of Plant Genetics and Crop Plant Research (Germany)
 14h05 Consistency of Derivative Based Functional Classifiers on Sampled Data
 
  • Fabrice Rossi, Projet AxIS - INRIA Paris Rocquencourt (FRANCE)
  • Nathalie Villa, Institut de Mathématiques de Toulouse (UMR 5219) - Université Paul Sabatier (Toulouse III) (FRANCE)
 14h25 Generalized matrix learning vector quantizer for the analysis of spectral data
 
  • Petra Schneider, Univerity Groningen - Mathematics and Computing Science - Intelligent Systems Group ( The Netherlands)
  • Frank-Michael Schleif, AG Computational Intelligence - University of Leipzig (Germany)
  • Thomas Villmann, University of Leipzig - Clinic for Psychotherapy (Germany)
  • Michael Biehl, University of Groningen - Mathematics and Computing Science (The Netherlands)
 14h45 Linear Projection based on Noise Variance Estimation - Application to Spectral Data
 
  • Amaury Lendasse, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)
  • Francesco Corona, Helsinki University of Technology - Laboratory of Computer and Information Science (Finland)

 15h05 Machine Learning Approaches and Pattern Recognition for Spectral Data
Poster spotlights
 15h05 Inverting hyperspectral images with Gaussian Regularized Sliced Inverse Regression
 
  • Caroline Bernard-Michel, MISTIS - INRIA Rhône-Alpes (France)
  • Sylvain Douté, Laboratoire de planétologie de Grenoble (France)
  • Laurent Gardes, MISTIS - INRIA Rhône-Alpes (France)
  • Stephane Girard, MISTIS - INRIA Rhône-Alpes (France)

 15h07 Poster spotlights
 15h07 Comparison of sparse least squares support vector regressors trained in primal and dual
 
  • Shigeo Abe, Graduate School of Engineering - Kobe University (Japan)
 15h08 On related violating pairs for working set selection in SMO algorithms
 
  • Tobias Glasmachers, Optimization of Adaptive Systems Group - Institut für Neuroinformatik - Ruhr-Universität Bochum (Germany)
 15h09 Discrimination of regulatory DNA by SVM on the basis of over- and under-represented motifs
 
  • Rene te Boekhorst, School of Computer Science - University of Hertfordshire (UK)
  • Irina Abnizova, Biostatistical unit - MRC - 01223 330388 (UK)
  • Lorenz Wernisch, MRC Biostatistics Unit Institute of Public Health (United Kingdom)
 15h10 Automatic alignment of medical vs. general terminologies
 
  • Laura Diosan, LITIS, INSA Rouen, France - Computer Science Department, Babes Bolyai University, - Cluj Napoca, Romania (Romania)
  • Alexandrina Rogozan, LITIS - INSA Rouen - France (France)
  • Jean Pierre Pecuchet, LITIS, EA 4081, INSA Rouen - France (France)
 15h11 Improving a statistical language model by modulating the effects of context words
 
  • Zhang Yuecheng, University of Toronto - Department of Computer Science (Canada)
  • Andriy Mnih, University of Toronto - Department of Computer Science (Canada)
  • Geoffrey Hinton, University of Toronto - Department of Computer Science (Canada)
 15h12 An emphasized target smoothing procedure to improve MLP classifiers performance
 
  • Soufiane El Jelali, University Carlos III de Madrid - Dpt. of Signal Processing and Communication (Spain)
  • Abdelouahid Lyhyaoui, University Carlos III de Madrid - Dpt .of Signal Processing and Communication (Spain)
  • Aníbal R. Figueiras-Vídal, University Carlos III de MAdrid - Dpt. of Signal Processing and Communication (Spain)
 15h13 A neural model with feedback for robust disambiguation of motion
 
  • Mauricio Cerda, LORIA- INRIA Nancy Grand Est - Cortex Team (France)
  • Bernard Girau, LORIA- INRIA Nancy Grand Est - Cortex Team (France)
 15h14 Multilayer perceptron to model the decarburization process in stainless steel production
 
  • Carlos Spínola, Departament of Electronics, Málaga University (Spain) (Spain)
  • Carlos J. Gálvez-Fernández, Department of Electronics, Málaga University (Spain) - TCC S.A (Spain)
  • José Muñoz-Pérez, Department of Languajes and Sciences of the Computation (Spain)
  • José Bonelo, Acerinox Co. (Spain)
  • Javier Ferrer, Acerinox Co. (Spain)
  • Julio Vizoso, Acerinox Co. (Spain)
 15h15 An automatic identifier of Confinement Regimes at JET combining Fuzzy Logic and Classification Trees
 
  • Guido Vagliasindi, Università degli Studi di Catania - Dipartimento di Ingegneria Elettrica, Elettronica e dei Sistemi (Italy)
  • Paolo Arena, Università degli Studi di Catania - Dipartimento di Ingegneria Elettrica, Elettronica e dei Sistemi (Italy)
  • Luigi Fortuna, Università degli Studi di Catania - Dipartimento di Ingegneria Elettrica, Elettronica e dei Sistemi (Italy)
  • Andrea Murari, Consorzio RFX – Associazione EURATOM ENEA per la Fusione (Italy)
  • Giuseppe Mazzitelli, Assoc. Euratom-ENEA sulla Fusione, C.R. Frascati (Italy)
  • Antonio Gallo, Università degli Studi di Catania - Dipartimento di Ingegneria Elettrica, Elettronica e dei Sistemi (Italy)
  • Umberto Vagliasindi, Università degli Studi di Catania - Dipartimento di Ingegneria Elettrica, Elettronica e dei Sistemi (Italy)
 15h17 Combining neural networks and optimization techniques for visuokinesthetic prediction and motor planning
 
  • Wolfram Schenck, Computer Engineering Group - Faculty of Technology - Bielefeld University (Germany)
  • Dennis Sinder, Computer Engineering Group - Faculty of Technology - Bielefeld University (Germany)
  • Ralf Möller, Computer Engineering Group - Faculty of Technology - Bielefeld University (Germany)
 15h18 Petri nets design based on neural networks
 
  • Edouard Leclercq, Université du Havre (France)
  • Souleiman Ould el Medhi, Université du Havre (France)
  • Dimitri Lefebvre, Université du Havre (France)
 15h19 Detecting zebra crossings utilizing AdaBoost
 
  • Ludwig Lausser, University Hospital Ulm (Germany)
  • Friedhelm Schwenker, Institute of Neural Information Processing - University of Ulm (Germany)
  • Günther Palm, Department of Neural Information Processing - University of Ulm (Germany)

 15h20 Coffee break and poster preview



 


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