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 ?

22nd European Symposium On Artificial Neural Networks, Computational Intelligence and Machine Learning
Bruges (Belgium), 23-24-25 April 2014

Programme

Wednesday April 23, 2014
 08h30 Registration

 09h00 Opening

 09h10 Advances in Spiking Neural Information Processing Systems (SNIPS)
Organized by Sander Bohte (Netherlands), Andre Gruning (UK)
 09h10 Spiking Neural Networks: Principles and Challenges
 
  • André Grüning, Department of Computing - Faculty of Engineering and Physical Sciences - University of Surrey (United Kingdom)
  • Sander Bohte, Centrum Wiskunde Informatica (The Netherlands)
 09h30 A new biologically plausible supervised learning method for spiking neurons
 
  • Aboozar Taherkhani, Intelligent Systems Research Centre - University of Ulster (U.K.)
  • Ammar Belatreche, Intelligent Systems Research Centre - University of Ulster (U.K.)
  • Yuhua Li, Intelligent Systems Research Centre - University of Ulster (U.K.)
  • Liam Maguire, Intelligent Systems Research Centre - University of Ulster (U.K.)
 09h50 Spiking AGREL
 
  • Davide Zambrano, The BioRobotics Institute - Scuola Superiore Sant'Anna (Italy)
  • Jaldert O. Rombouts, Centrum Wiskunde Informatica ( The Netherlands)
  • Cecilia Laschi, The BioRobotics Institute - Scuola Superiore Sant'Anna (Italy)
  • Sander Bohte, Centrum Wiskunde Informatica (The Netherlands)

 10h10 Advances in Spiking Neural Information Processing Systems (SNIPS)
Poster spotlights
 10h10 Classifying Patterns in a Spiking Neural Network
 
  • Brian Gardner, Department of Computing - Faculty of Engineering and Physical Sciences - University of Surrey (United Kingdom)
  • André Grüning, Department of Computing - Faculty of Engineering and Physical Sciences - University of Surrey (United Kingdom)
 10h11 Toward STDP-based population action in large networks of spiking neurons
 
  • Emmanuel Daucé, INSERM UMR 1106 - Institut de Neurosciences des Systèmes (France)

 10h12 Vector quantization- and nearest neighbour-based methods
 10h12 Supervised Generative Models for Learning Dissimilarity Data
 
  • David Nebel, University of Applied Sciences Mittweida (Germany)
  • Barbara Hammer, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida (Germany)
 10h32 Rejection strategies for learning vector quantization
 
  • Lydia Fischer, CoR-Lab (Research Institute for Cognition and Robotics), Bielefeld University - HONDA Research Institute Europe GmbH (Germany)
  • Barbara Hammer, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)
  • Heiko Wersing, HONDA Research Institute Europe GmbH (Germany)

 10h52 Vector quantization- and nearest neighbour-based methods
Poster spotlights
 10h52 Optimization of General Statistical Accuracy Measures for Classification Based on Learning Vector Quantization
 
  • Marika Kaden, University of Applied Sciences Mittweida (Germany)
  • Wieland Hermann, Paracelsus-Klinikum Zwickau - Abt. Neurologie (Germnay)
  • Thomas Villmann, University of Applied Sciences Mittweida (Germany)
 10h53 Augmented hashing for semi-supervised scenarios
 
  • Zalán-Péter Bodó, Babeș-Bolyai University, Faculty of Mathematics and Computer Science (Romania)
  • Lehel Csató, Babeș-Bolyai University, Faculty of Mathematics and Computer Science (Romania)
 10h54 Improving accuracy by reducing the importance of hubs in nearest-neighbor recommendations
 
  • François Fouss, Université catholique de Louvain (Belgique)
  • Clémentine Van Parijs, Université catholique de Louvain (Belgique)
 10h55 A new approach for multiple instance learning based on a homogeneity bag operator
 
  • Alexandre Wagner Chagas Faria, Universidade Federal de Minas Gerais - Graduate Program in Electrical Engineering (Brazil)
  • David Menotti, Universidade Federal de Ouro Preto - Computing Department (Brazil)
  • André P. Lemos, Federal University of Minas Gerais (Brazil)
  • Antônio P. Braga, Federal University of Minas Gerais (Brazil)

 10h56 Coffee break

 11h15 Byte the bullet: learning on real-world computing architectures
Organized by Davide Anguita, Alessandro Ghio, Luca Oneto (Italy)
 11h15 Byte The Bullet: Learning on Real-World Computing Architectures
 
  • Alessandro Ghio, DITEN - University of Genoa (Italy)
  • Luca Oneto, DITEN - University of Genoa (Italy)
 11h35 Learning with few bits on small-scale devices: From regularization to energy efficiency
 
  • Davide Anguita, DITEN - University of Genoa (Italy)
  • Alessandro Ghio, DITEN - University of Genoa (Italy)
  • Luca Oneto, DITEN - University of Genoa (Italy)
  • Sandro Ridella, DITEN - University of Genoa (Italy)
 11h55 Speedy greedy feature selection: Better redshift estimation via massive parallelism
 
  • Fabian Gieseke, University of Copenhagen - Department of Computer Science (Denmark)
  • Kai Polsterer, Heidelberg Institute for Theoretical Studies gGmbH - Astroinformatics (Germany)
  • Cosmin Eugen Oancea, University of Copenhagen - Department of Computer Science (Denmark)
  • Christian Igel, University of Copenhagen - Department of Computer Science (Denmark)
 12h15 Context- and cost-aware feature selection in ultra-low-power sensor interfaces
 
  • Steven Lauwereins, KU Leuven - ESAT-MICAS (Belgium)
  • Komail Badami, KU Leuven - ESAT-MICAS (Belgium)
  • Wannes Meert, KU Leuven - CS-DTAI (Belgium)
  • Marian Verhelst, KU Leuven - ESAT-MICAS (Belgium)

 12h35 Byte the bullet: learning on real-world computing architectures
Poster spotlights
 12h35 Lightning fast asynchronous distributed k-means clustering
 
  • Árpád Berta, University of Szeged (Hungary)
  • István Hegedűs, University of Szeged (Hungary)
  • Róbert Ormándi, University of Szeged (Hungary)

 12h36 Lunch

 14h00 Reinforcement learning and optimization
 14h00 Selective Neural Network Ensembles in Reinforcement Learning
 
  • Stefan Faußer, Institute of Neural Information Processing - University of Ulm (Germany)
  • Friedhelm Schwenker, Institute of Neural Information Processing - University of Ulm (Germany)
 14h20 Learning resets of neural working memory
 
  • Jaldert O. Rombouts, Centrum Wiskunde Informatica ( The Netherlands)
  • Pieter Roelfsema, Nederlands Herseninstituut (The Netherlands)
  • Sander Bohte, Centrum Wiskunde Informatica (The Netherlands)

 14h40 Reinforcement learning and optimization
Poster spotlights
 14h40 Naive Augmenting Q-Learning to Process Feature-Based Representations of States
 
  • Janis Zuters, University of Latvia - Faculty of Computing (Latvia)
 14h41 Direct Model-Predictive Control
 
  • Jean-Joseph Christophe, TAO INRIA (France)
  • Jérémie Decock, TAO INRIA (Cedex)
  • Olivier Teytaud, TAO INRIA (France)
 14h42 Ensembles of extreme learning machine networks for value prediction
 
  • Pablo Escandell-Montero, University of Valencia (Spain)
  • José María Martínez Martínez, University of Valencia (Spain)
  • Emilio Soria-Olivas, University of Valencia - Intelligent Data Analysis Laboratory (Spain)
  • Joan Vila-Francés, University of Valencia (Spain)
  • José David Martín-Guerrero, University of Valencia (Spain)
 14h43 An application of the temporal difference algorithm to the truck backer-upper problem
 
  • Christopher Gatti, RPI - ISYE (NY)
  • Mark Embrechts, RPI (USA)
 14h44 Application of Newton's Method to action selection in continuous state- and action-space reinforcement learning
 
  • Barry Nichols, University of Westminster (England)
  • Dimitris Dracopoulos, University of Westminster (England)
 14h45 Linear Scalarized Knowledge Gradient in the Multi-Objective Multi-Armed Bandits Problem
 
  • Saba Yahyaaa, Vub (Belgium)
  • Madalina Drugan, Vrije Universiteit Brussel (VUB) (Belgium)
  • Bernard Manderick, Vrije Universiteit Brussel (VUB) (Belgium)
 14h46 Improving the firefly algorithm through the Barnes-Hut tree code
 
  • Kiril Ralinovski, Berlin Institute of Technology - Department of Machine Learning (Germany)
 14h47 Improved Cat Swarm Optimization approach applied to reliability-redundancy problem
 
  • Carlos E. Klein, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
  • Leandro Coelho, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
  • Ângelo M. O. Sant’Anna, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
  • Roberto Z. Freire, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
  • Viviana C. Mariani, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Mechanical Engineering Graduate Program (PPGEM) (Brazil)

 14h48 Nonlinear dimensionality reduction
 14h48 Relevance Learning for Dimensionality Reduction
 
  • Alexander Schulz, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)
  • Andrej Gisbrecht, Bielefeld University - CITEC Center of Excellence - Cognitive Interaction Technology (Germany)
  • Barbara Hammer, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)
 15h08 Dimensionality reduction in decentralized networks by Gossip aggregation of principal components analyzers
 
  • Jérôme FELLUS, ETIS - UMR CNRS 8051 - ENSEA - Universite de Cergy-Pontoise (France)
  • David PICARD, ETIS - UMR CNRS 8051 - ENSEA - Universite de Cergy-Pontoise (France)
  • Philippe-Henri GOSSELIN, INRIA Bretagne, TexMex project (France)
 15h28 Multiscale stochastic neighbor embedding: Towards parameter-free dimensionality reduction
 
  • John A. Lee, Molecular Imaging, Radiotherapy, and Oncology - Université catholique de Louvain (Belgium)
  • Diego H. Peluffo-Ordonez, Machine Learning Group - Université catholique de Louvain (Belgium)
  • Michel Verleysen, Machine Learning Group - Université catholique de Louvain (Belgium)

 15h48 Nonlinear dimensionality reduction
Poster spotlights
 15h48 Interactive dimensionality reduction for visual analytics
 
  • Ignacio Diaz-Blanco, University of Oviedo (SPAIN)
  • Abel A. Cuadrado-Vega, University of Oviedo (SPAIN)
  • Daniel Perez-Lopez, University of Oviedo (SPAIN)
  • Francisco Garcia-Fernandez, University of Oviedo (SPAIN)
  • Michel Verleysen, Machine Learning Group - Université catholique de Louvain (Belgium)
 15h49 Recent methods for dimensionality reduction: A brief comparative analysis
 
  • Diego H. Peluffo-Ordonez, Machine Learning Group - Université catholique de Louvain (Belgium)
  • John A. Lee, Molecular Imaging, Radiotherapy, and Oncology - Université catholique de Louvain (Belgium)
  • Michel Verleysen, Machine Learning Group - Université catholique de Louvain (Belgium)

 15h50 Signal and temporal processing
 15h50 Capturing confounding sources of variation in DNA methylation data by spatiotemporal independent component analysis
 
  • Emilie Renard, Université catholique de Louvain - ICTEAM institute (Belgium)
  • Andrew Teschendorff, University College London - UCL Cancer Institute (United Kingdom)
  • Pierre-Antoine Absil, Université catholique de Louvain - ICTEAM institute (Belgium)
 16h10 Towards an effective multi-map self organizing recurrent neuronal network
 
  • Denis Baheux, Supelec -maLIS research team - UMI 2958 Georgia Tech/CNRS (France)
  • Hervé Frezza-Buet, Supélec (France)
  • Jeremy Fix, SUPELEC (France)

 16h30 Signal and temporal processing
Poster spotlights
 16h30 Iterative ARIMA-multiple support vector regression models for long term time series prediction
 
  • João Oliveira, Federal University of Pernambuco- Center of informatics (Brazil)
  • Teresa B. Ludermir, Universidade Federal de Pernambuco - Centro de Informática (Brazil)
 16h31 Region of interest detection using MLP
 
  • Tommi Kärkkäinen, University of Jyväskylä (Finland)
  • Alexandr Maslov, University of Jyväskylä (Finland)
  • Pekka Wartiainen, University of Jyväskylä (Finland)
 16h32 Analysis of the Weighted Fuzzy C-means in the problem of source location
 
  • Everton Z. Nadalin, University of Campinas (Brazil)
  • Rodrigo C. Silva, University of Campinas (Brazil)
  • Romis Attux, University of Campinas (Brazil)
  • João M. T. Romano, University of Campinas (Brazil)
 16h33 An Optimized Learning Algorithm Based on Linear Filters Suitable for Hardware implemented Self-Organizing Maps
 
  • Marta Kolasa, Faculty of Telecommunication and Electrical Engineering - University of Technology and Life Sciences (Poland)
  • Rafal Dlugosz, University of Technology and Life Sciences - Faculty of Telecommunication and Electrical Engineering (Poland)
  • Talaska Tomasz, Faculty of Telecommunication and Electrical Engineering - University of Technology and Life Sciences (Poland)
  • Pedrycz Witold, Department of Electrical and Computer Engineering - University of Alberta (Canada)
 16H34 Enhanced NMF initialization using a physical model for pollution source apportionment
 
  • Marc Plouvin, Laboratoire d’Informatique Signal et Image de la Côte d’Opale (LISIC) - Université du Littoral Côte d'Opale (ULCO) (France)
  • Abdelhakim Limem, Laboratoire d’Informatique Signal et Image de la Côte d’Opale (LISIC) - Université du Littoral Côte d'Opale (ULCO) (France)
  • Matthieu Puigt, Laboratoire d’Informatique Signal et Image de la Côte d’Opale (LISIC) - Université du Littoral Côte d'Opale (ULCO) (France)
  • Gilles Delmaire, Laboratoire d’Informatique Signal et Image de la Côte d’Opale (LISIC) - Université du Littoral Côte d'Opale (ULCO) (France)
  • Gilles Roussel, Laboratoire d’Informatique Signal et Image de la Côte d’Opale (LISIC) - Université du Littoral Côte d'Opale (ULCO) (France)
  • Dominique Courcot, Unité de Chimie Environnementale et Interactions sur le Vivant (UCEIV) - Université du Littoral Côte d'Opale (ULCO) (France)
 16h35 A New Error-Correcting Syndrome Decoder with Retransmit Signal Implemented with an Hardlimit Neural Network
 
  • Jose Fonseca, Department of Electrical Engineering - Faculty of Sciences and Technology - New University of Lisbon (Portugal)

 16h36 Coffee break and poster preview


Thursday April 24, 2014b>
 09h00 Learning of structured and non-standard data
Organized by Frank-Michael Schleif, Thomas Villmann, Peter Tino (Germany & UK)
 09h00 Recent trends in learning of structured and non-standard data
 
  • Frank-Michael Schleif, University of Birmingham - School of Computer Science (UK)
  • Peter Tino, The University of Birmingham (UK)
  • Thomas Villmann, University of Applied Sciences Mittweida (Germany)
 09h20 Support Vector Ordinal Regression using Privileged Information
 
  • Fengzhen Tang, The University of Birmingham (UK)
  • Peter Tino, The University of Birmingham (UK)
  • Pedro Antonio Gutiérrez, University of Córdoba (Spain)
  • Huanhuan Chen, The University of Birmingham (UK)
 09h40 Segmented shape-symbolic time series representation
 
  • Herbert Teun Kruitbosch, University of Groningen - Johann Bernoulli Institute (The Netherlands)
  • Ioannis Giotis, Target Holding BV (Netherlands)
  • Michael Biehl, University of Groningen - Johann Bernoulli Institute for Mathematics and Computer Science (The Netherlands)
 10h00 Adaptive distance measures for sequential data
 
  • Bassam Mokbel, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)
  • Benjamin Paassen, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)
  • Barbara Hammer, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)

 10h20 Learning of structured and non-standard data
Poster spotlights
 10h20 Applications of lp-Norms and their Smooth Approximations for Gradient Based Learning Vector Quantization
 
  • Mandy Lange, University of Applied Sciences Mittweida (Germany)
  • Dietlind Zühlke, Fraunhofer-IAIS - Knowledge Discovery, Integrated Data Mining (Germany)
  • Olaf Holz, Fraunhofer-ITEM (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida (Germany)
 10h21 Utilization of Chemical Structure Information for Analysis of Spectra Composites
 
  • Kristin Domaschke, Life Science Inkubator Sachsen GmbH & Co.KG - Projektgruppe NanoscopiX (Germany)
  • André Roßberg, Helmholtz-Zentrum Dresden-Rossendorf - Molecular Structures (Germany)
  • Thomas Villmann, University of Applied Sciences Mittweida (Germany)
 10h22 Weighted tree kernels for sequence analysis
 
  • Christopher Bowles, School of EECS, QUT (Australia)
  • James Hogan, School of EECS, QUT (Australia)

 10h23 Coffee break

 10h45 Kernel methods
 10h45 Easy multiple kernel learning
 
  • Fabio Aiolli, Dept. of Mathematics - University of Padova (Italy)
  • Michele Donini, University of Padova - Department of Mathematics (Italy)
 11h05 Joint SVM for Accurate and Fast Image Tagging
 
  • Hanchen Xiong, Institute of Computer Science,University of Innsbruck (Austria)
  • Sandor Szedmak, Institute of Computer Science - University of Innsbruck (Austria)
  • Justus Piater, Institute of Computer Science,University of Innsbruck (Austria)
 11h25 Kernel methods for mixed feature selection
 
  • Jérôme Paul, Université catholique de Louvain (Belgium)
  • Pierre Dupont, Université catholique de Louvain (Belgium)
 11h45 The one-sided mean kernel: a positive definite kernel for time series
 
  • Nicolas Chrysanthos, Institut Charles Delaunay (UMR CNRS 6279 STMR), LM2S - Université de Technologie de Troyes (France)
  • Pierre Beauseroy, Institut Charles Delaunay (UMR CNRS 6279 STMR), LM2S - Université de Technologie de Troyes (France)
  • Hichem Snoussi, Institut Charles Delaunay (UMR CNRS 6279 STMR), LM2S - Université de Technologie de Troyes (France)
  • Edith Grall-Maës, Institut Charles Delaunay (UMR CNRS 6279 STMR), LM2S - Université de Technologie de Troyes (France)
  • Fabrice Ferrand, Sagem Défense Sécurité (France)
 12h05 A robust regularization path for the Doubly Regularized Support Vector Machine
 
  • Antoine Lachaud, CEA LIST (France)
  • Stéphane Canu, LITIS, INSA de Rouen, Normandie Université (France)
  • David Mercier, CEA LIST (France)
  • Frederic Suard, CEA LIST (France)

 12h25 Kernel methods
Poster spotlights
 12h25 Tensor decomposition of dense SIFT descriptors in object recognition
 
  • Tan Vo, University of Canberra (Australia)
  • Dat Tran, University of Canberra (Australia)
  • Ma Wanli, University of Canberra (Australia)
 12h26 Fine-tuning of support vector machine parameters using racing algorithms
 
  • Péricles Miranda, Universidade Federal de Pernambuco, Centro de Informática (Brazil)
  • Ricardo Silva, Universidade Federal de Pernambuco, Centro de Informática (Brazil)
  • Ricardo Prudêncio, Universidade Federal de Pernambuco, Centro de Informática (Brazil)
 12h27 reject option paradigm for the reduction of support vectors
 
  • Sousa Ricardo, Instituto de Telecomunicações, Faculdade de Ciências da Universidade do Porto (Portugal)
  • Ajalmar R. da Rocha Neto, IFCE (Brazil)
  • Guilherme Barreto, Departamento Engenharia de Teleinformatica, Universidade Federal do Ceará (Brazil)
  • Jaime S. Cardoso, INESC TEC, FEUP (Portugal)
  • Miguel T. Coimbra, IT, FCUP (Portugal)
 12h28 The Choquet kernel for monotone data
 
  • Ali Fallah Tehrani, Philipps Universität Marburg (Germany)
  • Marc Strickert, Philipps Universität Marburg (Germany)
  • Eyke Hüllermeier, Philipps Universität Marburg (Germany)

 12h29 Lunch

 13h50 Learning and Modeling Big Data
Organized by Barbara Hammer, Haibo He, Thomas Martinetz (Germany & USA)
 13h50 Learning and modeling big data
 
  • Barbara Hammer, CITEC (Cognitive Interaction Technology Center of Excellence) - Bielefeld University (Germany)
  • Haibo He, University of Rhode Island (U.S.A.)
  • Thomas Martinetz, University of Luebeck (Germany)
 14h10 Agglomerative hierarchical kernel spectral clustering for large scale networks
 
  • Mall Raghvendra, KU Leuven (Belgium)
  • Langone Rocco, KU Leuven (Belgium)
  • Suykens Johan, KU Leuven (Belgium)
 14h30 Proximity learning for non-standard big data
 
  • Frank-Michael Schleif, University of Birmingham - School of Computer Science (UK)

 14h50 Learning and Modeling Big Data
Poster spotlights
 14h50 Predicting Grain Protein Content of Winter Wheat
 
  • Mansouri Majdi, Département des Sciences et Technologies de l’Environnement, GxABT, Université de Liège (Belgium)
  • Marie-France Destain , Département des Sciences et Technologies de l’Environnement, GxABT, Université de Liège (Belgium)
  • Benjamin Dumont, Département des Sciences et Technologies de l'Environnement, - Université de Liège (GxABT) (Belgium)

 14h51 Classification
 14h51 On the complexity of shallow and deep neural network classifiers
 
  • Monica Bianchini, Dipartimento di Ingegneria dell'Informazione e Scienze Matematiche - Università degli Studi di Siena (Italy)
  • Franco Scarselli, Dipartimento di Ingegneria dell'Informazione e Scienze Matematiche - Università  degli Studi di Siena (Italy)
 15h11 Evidence build-up facilitates on-line adaptivity in dynamic environments: example of the BCI P300-speller
 
  • Emmanuel Daucé, INSERM UMR 1106 - Institut de Neurosciences des Systèmes (France)
  • Eoin Thomas, INRIA Lille Nord Europe (France)
 15h31 Choosing the Metric in High-Dimensional Spaces Based on Hub Analysis
 
  • Dominik Schnitzer, OFAI (Austria)
  • Arthur Flexer, OFAI (Austria)
 15h51 Robust outlier detection with L0-SVDD
 
  • Meriem El Azami, Université de Lyon CREATIS; CNRS UMR5220; INSERM U1044; - INSA-Lyon; Univ. Lyon 1 (France)
  • Carole Lartizien, Université de Lyon CREATIS; CNRS UMR5220; INSERM U1044; - INSA-Lyon; Univ. Lyon 1 (France)
  • Stéphane Canu, LITIS, INSA de Rouen, Normandie Université (France)

 16h11 Classification
Poster spotlights
 16h11 Toward parallel feature selection from vertically partitioned data
 
  • Veronica Bolon-Canedo, University of A Coruña (Spain)
  • Noelia Sanchez-Maroño, University of A Coruña (Spain)
  • Joana Cervino-Rabunal, University of A Coruña (Spain)
 16h12 Modeling consumption of contents and advertising in online newspapers
 
  • Iago Porto-Díaz, University of A Coruña (Spain)
  • David Martínez-Rego, University of A Coruña (Spain)
  • Oscar Fontenla-Romero, University of A Coruña (Spain)
  • Amparo Alonso-Betanzos, University of A Coruña (Spain)
 16h13 Reweighted l1 Dual Averaging Approach for Sparse Stochastic Learning
 
  • Jumutc Vilen, KU Leuven, ESAT-STADIUS (Belgium)
  • Suykens Johan, KU Leuven (Belgium)
 16h14 Using Shannon Entropy as EEG Signal Feature for Fast Person Identification
 
  • Dinh Phung, University of Canberra - Faculty of Education, Science, Technology and Mathematics (Australia)
  • Dat Tran, University of Canberra (Australia)
  • Ma Wanli, University of Canberra (Australia)
  • Phuoc Nguyen, University of Canberra - Faculty of Education, Science, Technology and Mathematics (Australia)
  • Pham Tien, University of Canberra - Faculty of Education, Science, Technology and Mathematics (Australia)
 16h15 Machine learning techniques to assess the performance of a gait analysis system
 
  • Sébastien Piérard, University of Liège - Montefiore Institute - INTELSIG Laboratory (Belgium)
  • Rémy Phan-Ba, University of Liège (Belgium)
  • Marc Van Droogenbroeck, University of Liège - Montefiore Institute - INTELSIG Laboratory (Belgium)
 16h16 A Random Forest proximity matrix as a new measure for gene annotation
 
  • Jose A. Seoane, Bristol Genetic Epidemiology Laboratory - School of Social and Community Medicine - University of Bristol (United Kingdom)
  • Ian N.M. Day, Bristol Genetic Epidemiology Laboratory - School of Social and Community Medicine - University of Bristol (United Kingdom)
  • Juan P. Casas, Department of Non-communicable Disease Epidemiology - London School of Hygiene and Tropical Medicine (United Kingdom)
  • Colin Campbell, Intelligent Systems Laboratories - University of Bristol (United Kingdom)
  • Tom R. Gaunt, Bristol Genetic Epidemiology Laboratory - MRC Integrative Epidemiology Unit - School of Social and Community Medicine - University of Bristol (United Kingdom)
 16h17 Neural network based 2D/3D fusion for robotic object recognition
 
  • Louis-Charles Caron, ENSTA ParisTech (France)
  • Yang Song, ENSTA ParisTech (France)
  • Filliat David, ENSTA ParisTech (France)
  • Alexander Gepperth, ENSTA ParisTech (France)
 16h18 Discrimination of visual pedestrians data by combining projection and prediction learning
 
  • Mathieu Lefort, ENSTA ParisTech (France)
  • Alexander Gepperth, ENSTA ParisTech (France)
 16h19 FINGeR: Framework for interactive neural-based gesture recognition
 
  • German Ignacio Parisi, University of Hamburg - Department of Computer Science (Germany)
  • Pablo Barros, University of Hamburg - Department of Computer Science (Germany)
  • Stefan Wermter, University of Hamburg - Department of Computer Science (Germany)
 16h20 Beyond histograms: why learned structure-preserving descriptors outperform HOG
 
  • Thomas Guthier, TU Darmstadt - Control Theory and Robotics Lab (Germany)
  • Volker Willert, TU Darmstadt - Control Theory and Robotics Lab (Germany)
  • Julian Eggert, Honda Research Institute Europe GmbH (Germany)
 16h21 NMF-Density: NMF-Based Breast Density Classifier
 
  • Lahouari Ghouti, King Fahd University of Petroleum and Minerals - College of Computer Sciences and Engineering - Department of Information and Computer Science (Saudi Arabia)
  • Abdullah Owaidh, King Fahd University of Petroleum and Minerals - Department of Information and Computer Science (Saudi Arabia)

 16h22 Dynamical systems and online learning
 16h22 Implicitly and explicitly constrained optimization problems for training of recurrent neural networks
 
  • Carl-Johan Thore, Linköping University - Department of Management and Engineering - Division of Mechanics (Sweden)
 16h42 A HMM-based pre-training approach for sequential data
 
  • Luca Pasa, University of Padua, Department of Mathematics (Italy)
  • Alberto Testolin, University of Padova, Deparment of Developmental Psychology and Socialisation (Italy)
  • Alessandro Sperduti, University of Padua, Department of Mathematics (Italy)

 17h02 Dynamical systems and online learning
Poster spotlights
 17h02 Exploiting similarity in system identification tasks with recurrent neural networks
 
  • Sigurd Spieckermann, Siemens AG, Corporate Technology, Learning Systems (Germany)
  • Siegmund Düll, Siemens AG, Corporate Technology, Learning Systems (Germany)
  • Steffen Udluft, Siemens AG, Corporate Technology, Learning Systems (Germany)
  • Alexander Hentschel, Siemens AG, Corporate Technology, Learning Systems (Germany)
  • Thomas Runkler, Siemens AG, Corporate Technology, Learning Systems (Germany)
 17h04 Comparison of local and global undirected graphical models
 
  • Zhemin Zhu, Electrical Engineering, Mathematics and Computer Science (EEMCS) - University of Twente (Netherlands)
  • Djoerd Hiemstra, Electrical Engineering, Mathematics and Computer Science (EEMCS) - University of Twente (Netherlands)
  • Peter Apers, Electrical Engineering, Mathematics and Computer Science (EEMCS) - University of Twente (Netherlands)
  • Andreas Wombacher, University of Twente (Netherlands)
 17h05 Meta Online Learning: Experiments on a Unit Commitment Problem
 
  • Jialin Liu, TAO INRIA (France)
  • Olivier Teytaud, TAO INRIA (France)
 17h06 DELA: A Dynamic Online Ensemble Learning Algorithm
 
  • Hamid Bouchachia, Bournemouth University - Department of Computing - School of Design, Engineering & Computing (UK)
  • Emili Balaguer-Ballester, Bournemouth University - Department of Computing - School of Design, Engineering & Computing (UK)

 17h07 Coffee break and poster preview


Friday April 25, 2014
 09h00 Advances on Weightless Neural Systems
Organized by Massimo De Gregorio, Priscila M.V. Lima, Wilson R. de Oliveira (Italy & Brazil)
 09h00 Advances on Weightless Neural Systems
 
  • Massimo De Gregorio, Istituto di Cibernetica (Italy)
  • Felipe M. G. França, Universidade Federal do Rio de Janeiro - COPPE/PESC/UFRJ (Brazil)
  • Priscila M. V. Lima, Universidade Federal Rural do Rio de Janeiro - Instituto de Ciências Exatas - Departamento de Matemática (Brazil)
  • Wilson R. de Oliveira, Universidade Federal Rural de Pernambuco - Departamento de Estatística e Informática (Brazil)
 09h20 Learning state prediction using a weightless neural explorer
 
  • Igor Aleksander, Imperial College (UK)
  • Helen Morton, Imperial College (UK)
 09h40 Can you follow that guy?
 
  • Mariacarla Staffa, Department of Electrical Engineering and Information Technology D.I.E.T.I. - University of Naples Federico II (Italy)
  • Massimo De Gregorio, Istituto di Cibernetica (Italy)
  • Maurizio Giordano, Istituto di Cibernetica (Italy)
  • Silvia Rossi, Department of Electrical Engineering and Information Technology D.I.E.T.I. - University of Naples Federico II (Italy)
 10h00 Credit analysis with a clustering RAM-based neural classifier
 
  • Douglas Cardoso, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Danilo Carvalho, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Daniel Alves, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Diego Souza, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Hugo Carneiro, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Carlos Pedreira, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Priscila M. V. Lima, Universidade Federal Rural do Rio de Janeiro - Instituto de Ciências Exatas - Departamento de Matemática (Brazil)
  • Felipe M. G. França, Universidade Federal do Rio de Janeiro - COPPE/PESC/UFRJ (Brazil)
 10h20 Training a classical weightless neural network in a quantum computer
 
  • Adenilton J. da Silva, Universidade Federal de Pernambuco - Centro de Informática (Brazil)
  • Wilson R. de Oliveira, Universidade Federal Rural de Pernambuco - Departamento de Estatística e Informática (Brazil)
  • Teresa B. Ludermir, Universidade Federal de Pernambuco - Centro de Informática (Brazil)

 10h40 Advances on Weightless Neural Systems
Poster spotlights
 10h40 Extracting rules from DRASiW’s "mental images"
 
  • Paulo Coutinho, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Hugo Carneiro, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Danilo Carvalho, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Felipe M. G. França, Universidade Federal do Rio de Janeiro - COPPE/PESC/UFRJ (Brazil)
 10h41 Vector space weightless neural networks
 
  • Wilson R. de Oliveira, Universidade Federal Rural de Pernambuco - Departamento de Estatística e Informática (Brazil)
  • Adenilton J. da Silva, Universidade Federal de Pernambuco - Centro de Informática (Brazil)
  • Teresa B. Ludermir, Universidade Federal de Pernambuco - Centro de Informática (Brazil)
 10h42 Online tracking of multiple objects using WiSARD
 
  • Rafael Lima de Carvalho, Universidade Federal do Tocantins - Curso de Ciência da Computação (Brazil)
  • Danilo Carvalho, UFRJ - Universidade Federal do Rio de Janeiro (Brazil)
  • Priscila M. V. Lima, Universidade Federal Rural do Rio de Janeiro - Instituto de Ciências Exatas - Departamento de Matemática (Brazil)
  • Felix Mora-Camino, École nationale de l'aviation civile - Laboratoire d'automatique (France)
  • Felipe M. G. França, Universidade Federal do Rio de Janeiro - COPPE/PESC/UFRJ (Brazil)
 10h43 Probabilistic automata simulation with single layer weightless neural networks
 
  • Adenilton J. da Silva, Universidade Federal de Pernambuco - Centro de Informática (Brazil)
  • Wilson R. de Oliveira, Universidade Federal Rural de Pernambuco - Departamento de Estatística e Informática (Brazil)
  • Teresa B. Ludermir, Universidade Federal de Pernambuco - Centro de Informática (Brazil)

 10h44 Coffee break

 11h05 Clustering
 11h05 Optimal Data Projection for Kernel Spectral Clustering
 
  • Diego H. Peluffo-Ordonez, Machine Learning Group - Université catholique de Louvain (Belgium)
  • Carlos Alzate, IBM Research - Ireland (Ireland)
  • Suykens Johan, KU Leuven (Belgium)
  • Germán Castellanos-Domínguez, Universidad Nacional de Colombia - Manizales (Colombia)
 11h25 Supporting GNG-based clustering with local input space histograms
 
  • Jochen Kerdels, University of Hagen - Faculty of Mathematics and Computer Science - Chair of Human-Computer Interaction (Germany)
  • Gabriele Peters, University of Hagen - Faculty of Mathematics and Computer Science - Chair of Human-Computer Interaction (Germany)
 11h45 The Sum-over-Forests clustering
 
  • Mathieu Senelle, Université catholique de Louvain (UCL) (Belgium)
  • Marco Saerens, Université catholique de Louvain (UCL) (Belgium)
  • François Fouss, Université catholique de Louvain (Belgique)

 12h05 Clustering
Poster spotlights
 12h05 Bayesian non-parametric parsimonious clustering
 
  • Faicel Chamroukhi, Université de Toulon, CNRS, LSIS, UMR 7296 (France)
  • Marius Bartcus, Université de Toulon, CNRS, LSIS, UMR 7296 (France)
  • Hervé Glotin, Université de Toulon, CNRS, LSIS, UMR 7296 (France)
 12h06 Learning predictive partitions for continuous feature spaces
 
  • Björn Weghenkel, Institut für Neuroinformatik (Germany)
  • Laurenz Wiskott, Institut für Neuroinformatik (Germany)
 12h07 An adjustable p-exponential clustering algorithm
 
  • Valmir Macario, Universidade Federal Rural de Pernambuco (Brazil)
  • Francisco de Assis Tenório De Carvalho, Universidade Federal de Pernambuco (Brazil)
 12h08 Self-organizing map for determination of goal candidates in mobile robot exploration
 
  • Jan Faigl, Department of Computer Science and Engineering - Faculty of Electrical Engineering - Czech Technical University in Prague (Czech Republic)
  • Peter Vanìk, Department of Computer Science and Engineering - Faculty of Electrical Engineering - Czech Technical University in Prague (Czech Republic)
  • Miroslav Kulich, Department of Cybernetics - Faculty of Electrical Engineering - Czech Technical University in Prague (Czech Republicb)

 12h09 Regression, Forceasting and Extreme Learning Machines
 12h09 Parameter-free regularization in Extreme Learning Machines with affinity matrices
 
  • Leonardo Silvestre, Federal University of Espírito Santo (Brazil)
  • André P. Lemos, Federal University of Minas Gerais (Brazil)
  • João P. Braga, Federal University of Minas Gerais (Brazil)
  • Antônio P. Braga, Federal University of Minas Gerais (Brazil)

 12h29 Regression, Forceasting and Extreme Learning Machines
Poster spotlights
 12h29 Feature selection in environmental data mining combining Simulated Annealing and Extreme Learning Machine
 
  • Michael Leuenberger, University of Lausanne - Faculty of Geosciences and Environment (Switzerland)
  • Mikhail Kanevski, University of Lausanne - Faculty of Geosciences and Environment (Switzerland)
 12h30 Mobility Prediction Using Fully-Complex Extreme Learning Machines
 
  • Lahouari Ghouti, King Fahd University of Petroleum and Minerals - College of Computer Sciences and Engineering - Department of Information and Computer Science (Saudi Arabia)
 12h31 An Extreme Learning Approach to Active Learning
 
  • Euler Horta, Universidade Federal dos Vales do Jequitinhonha e Mucuri (Brazil)
  • Antônio P. Braga, Federal University of Minas Gerais (Brazil)
 12h32 A new model selection approach for the ELM network using metaheuristic optimization
 
  • Ananda Freire, Federal University of Ceará (Brazil)
  • Guilherme Barreto, Departamento Engenharia de Teleinformatica, Universidade Federal do Ceará (Brazil)
 12h33 Extreme learning machines for Internet traffic classification
 
  • Joseph Ghafari, Orange Labs - Ecole des Mines de Nantes (France)
  • Emmanuel Herbert, Orange Labs (France )
  • Stephane Senecal, Orange Labs (France)
  • Daniel Migault, Orange Labs (France)
  • Stanislas Francfort, Orange Labs (France)
  • Ting Liu, Orange Labs (France)
 12h34 Electric load forecasting using wavelet transform and extreme learning machine
 
  • Song Li, Nanyang Technological University (Singapore)
  • Peng Wang, Nanyang Technological University (Singapore)
  • Lalit Goel, Nanyang Technological University (Singapore)
 12h35 Swim velocity profile identification through a Dynamic Self-adaptive Multiobjective Harmonic Search and RBF neural networks
 
  • Helon V. H. Ayala, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
  • Luciano F. da Cruz, Pontifical Catholic University of Parana (PUCPR) - Polytechnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
  • Leandro Coelho, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
  • Roberto Z. Freire, Pontifical Catholic University of Parana (PUCPR) - Politecnic School - Industrial and Systems Engineering Graduate Program (PPGEPS) (Brazil)
 12h36 Dynamic ensemble selection and instantaneous pruning for regression
 
  • Kaushala Dias, University of Surrey (United Kingdom)
  • Terry Windeatt, University of Surrey (United Kingdom)
 12h37 Data normalization and supervised learning to assess the condition of patients with multiple sclerosis based on gait analysis
 
  • Samir Azrour, University of Liège - Montefiore Institute - INTELSIG Laboratory (Belgium)
  • Sébastien Piérard, University of Liège - Montefiore Institute - INTELSIG Laboratory (Belgium)
  • Pierre Geurts, University of Liège - Montefiore Institute (Belgium)
  • Marc Van Droogenbroeck, University of Liège - Montefiore Institute - INTELSIG Laboratory (Belgium)
 12h38 Sparse one hidden layer MLPs
 
  • Alberto Torres, Universidad Autónoma de Madrid - Escuela Politécnica Superior (Spain)
  • David Díaz, Universidad Autónoma de Madrid - Escuela Politécnica Superior (Spain)
  • José R. Dorronsoro, Universidad Autónoma de Madrid - Escuela Politécnica Superior - Departamento de Ingeniería Informática (Spain)
 12h39 Multi-Step Ahead Forecasting of Road Condition Using Least Squares Support Vector Regression
 
  • Konsta Sirvio, Department of Information and Computer Science, Aalto University School of Science (Finland)
  • Jaakko Hollmén, Department of Information and Computer Science, Aalto University School of Science (Finland)

 12h40 Lunch

 14h00 Label noise in classification
Organized by Benoît Frénay, Ata Kaban (Belgium and UK)
 14h00 A comprehensive introduction to label noise
 
  • Benoît Frénay, Université catholique de Louvain (Belgium)
  • Ata Kaban, University of Birmingham (UK)
 14h20 Improving the Robustness of Bagging with Reduced Sampling Size
 
  • Maryam Sabzevari, Escuela Politécnica Superior - Universidad Autónoma de Madrid (Spain)
  • Gonzalo Martínez-Muñoz, Escuela Politécnica Superior - Universidad Autónoma de Madrid (Spain)
  • Alberto Suárez, Escuela Politécnica Superior - Universidad Autónoma de Madrid (Spain)
 14h40 Credal decision trees in noisy domains
 
  • Carlos J. Mantas, Department of Computer Science and Artificial Intelligence , University of Granada (Spain)
  • Joaquín Abellán, Department of Computer Science and Artificial Intelligence , University of Granada (Spain)
 15h00 Finding Originally Mislabels with MD-ELM
 
  • Anton Akusok, Aalto University - Department of Information and Computer Science (Finland)
  • David Veganzones, Univ. del Pais Vasco - Dept. of Computer Science & Artificial Intelligence (Spain)
  • Yoan Miche, Aalto University - Department of Information and Computer Science (Finland)
  • Eric Severin, University of Lille 1, IAE (France)
  • Amaury Lendasse, Arcada Univ. of Applied Science (Finland)

 15h20 Label noise in classification
Poster spotlights
 15h20 Misclassification of class C G-protein-coupled receptors as a label noise problem
 
  • Caroline König, Universidad Politècnica de Cataluña (UPC) - Dept. Lenguajes y Sistemas Informaticos (LSI) - Barcelona Tech (Spain)
  • Alfredo Vellido Alcacena, Univ. Politècnica de Catalunya - Dept. Llenguatges y Sistemes Informàtics (LSI) - Barcelona Tech (Spain)
  • René Alquézar Mancho, Univ. Politècnica de Catalunya - Dept. Llenguatges y Sistemes Informàtics (LSI) - Barcelona Tech (Spain)
  • Jesús Giraldo , Universitat Autònoma de Barcelona (UAB) - Institut de Neurociències and Unitat de Bioestadistica - Facultat de Medicina (Spain)
 15h21 A multi-class extension for multi-labeler support vector machines
 
  • Diego H. Peluffo-Ordonez, Machine Learning Group - Université catholique de Louvain (Belgium)
  • Santiago Murillo-Rendón, Universidad Nacional de Colombia - Manizales (Colombia)
  • Julián Arias-Londoño, Universidad de Antioquia (Colombia)
  • Germán Castellanos-Domínguez, Universidad Nacional de Colombia - Manizales (Colombia)

 15h23 Coffee break and poster preview

 17h00 End of conference



 

 

 


 


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