| Wednesday 21st April 1999 | |
| 8H30 | Registration |
| 9H00 | Opening |
| Session 1: Dynamical systems | |
| 9H00 | Synchronizing chaotic neuromodules F. Pasemann, Max-Planck Inst. (Germany) |
| 9H20 | Mean-field equations reveal synchronization in a 2-populations neural network model E. Daucé, O. Moynot, O. Pinaud, M. Samuelides, ONERA Toulouse, B. Doyon, CHU Purpan (France) |
| Session 2: Self-organization | |
| 9H40 | A hierarchical self-organizing feature map for analysis of not well separable clusters of different feature density S. Schünemann, B. Michaelis, Univ. Magdeburg (Germany) |
| 10H00 | Using the Kohonen algorithm for quick initialization of Simple Competitive Learning algorithm E. de Bodt1,2, M. Cottrell3, M. Verleysen1, 1Univ. Cat. Louvain (Belgium), 2Univ. Lille 2, 3Univ. Paris 1 (France) |
| 10H20 | Coffee break |
| Special session 3: Adaptive computation of data structures Organised by: Marco Gori, Univ. di Siena (Italy) |
|
| 10H40 | Learning in structured domains M. Gori, Univ. di Siena (Italy) |
| 11H00 | Approximation capabilities of folding networks B. Hammer, Univ. of Osnabrück (Germany) |
| 11H20 | Tree-recursive computation of gradient information for structures A. Kuechler, Univ. of Ulm (Germany) |
| 11H40 | Learning search-control heuristics for automated deduction systems with folding architecture networks C. Goller, TU Univ. of Munich (Germany) |
| 12H00 | A topological transformation for hidden recursive models F. Costa, P. Frasconi, G. Soda, Univ. of. Florence (Italy) |
| 12H20 | Lunch |
| Session 4: Methodology | |
| 14H00 | The application of neural networks to the paper-making industry P.J. Edwards, A. F. Murray, G. Papadopoulos, A.R. Wallace, Edinburgh Univ., J. Barnard, Tullis Russell (Scotland) |
| 14H20 | Marble slabs quality classification system using texture recognition and neural networks methodology J. Martinez-Cabeza de Vaca Alajarin, L.-M. Tomas Balibrea, Univ. de Murcia (Spain) |
| 14H40 | Visual-based posture recognition using hybrid neural networks A. Corradini, H.-J. Boehme, H.-M. Gross, Tech. Univ. of Ilmenau (Germany) |
| 15H00 | Model clustering by deterministic annealing B. Bakker, T. Heskes, Univ. of Nijmegen (Netherlands) |
| 15H20 | Coffee break |
| Special session 5: Remote sensing spectral image analysis Organised by: Erzsebet Merenyi, Univ. of Arizona (USA) |
|
| 15H40 | The challenges in spectral image analysis: an introduction, and review of ANN approaches E. Merenyi, Univ. of Arizona (USA) |
| 16H00 | A simple associative neural network for producing spatially homogenous spectral abundance interpretations of hyperspectral imagery N. Pendock, Univ. of the Witwatersrand (South Africa) |
| 16H20 | Estimating the intrinsic dimensionality of hyperspectral images J. Bruske, Christian-Albrechts-Univ. Kiel (Germany), E. Merenyi, Univ. of Arizona (USA) |
| 16H40 | Benefits and limits of the self-organizing map and its variants in the area of satellite remote sensoring processing T. Villmann, Univ. Leipzig (Germany) |
| Poster session: spotlights | |
| 17H00 | Comparison of Kohonen, scale-invariant and GTM self-organising maps for interpretation of spectral data D. MacDonald, S. McGlinchey, J. Kawala, C. Fyfe, Univ. of Paisley (UK) |
| 17H02 | Neural learning of approximate simple regular languages M. Forcada, A. Corbi, Univ. d’Alacant (Spain), M. Gori, M. Maggini, Univ. di Siena (Italy) |
| 17H04 | A benchmark for testing adaptive systems on structured data M. Hagenbuchner, A.C. Tsoi, Univ. of Wollongong (Australia) |
| 17H06 | AdaBoost and neural networks T. Windeatt, R. Ghaderi, Univ. of Surrey (UK) |
| 17H08 | Modeling face recognition learning in early infant development F. Acerra, Y. Burnod, Univ. Paris 6, S. de Schonen, Univ. Paris 5 (France) |
| 17H10 | The NeuralBAG algorithm: optimizing generalization performance in bagged neural networks J. Carney, P. Cunningham, Univ. of Dublin (Ireland) |
| 17H12 | Neuro-wavelet parametric characterization of hardness profiles V. Colla1, L. Reyneri2, M. Sgarbi1, 1Scuola Sup. Sant’Anna, 2Polit. di Torino (Italy) |
| 17H14 | Heterogeneity enhanced order in a chaotic neural network S. Mizutani, K. Shimohara, NTT Communic. Science Lab. (Japan) |
| 17H16 | Tackling the stability/plasticity dilemma with double loop dynamic systems C. Lecerf, Univ. Paris 8 (France) |
| 17H18 | Poster preview |
| Thursday 22nd April 1999 | |
| Session 6: Biological models and inspiration | |
| 9H00 | Regularization in oculomotor adaptation J. Bullinaria, P. Riddell, S. Rushton, Univ. of Reading (UK) |
| 9H20 | Recurrent V1-V2 interaction for early visual information processing H. Neumann, W. Sepp, Univ. Ulm (Germany) |
| 9H40 | Neural field description of state-dependent receptive field changes in the visual cortex K. Suder, F. Wörgötter, Ruhr-Univ. Bochum, T. Wennekers, Univ. of Ulm (Germany) |
| 10H00 | Coffee break |
| Special session 7: Support Vector Machines Organised by: S. Canu, INSA Rouen, PSI (France), Bernhard Schoelkopf, GMD FIRST Berlin (Germany) |
|
| 10H20 | Introduction to Support Vector Machines S. Canu, INSA Rouen, PSI (France) |
| 10H50 | Integrating the evidence framework and the support vector machine J. Kwok, Hong Kong Baptist Univ. (Hong Kong) |
| 11H10 | Support vector classifier with asymetric kernel function K. Tsuda, Electrotechnical laboratory (Japan) |
| 11H30 | A multiplicative updating algorithm for training support vector machine N. Cristianini, C. Campbell, Univ. of Bristol, J. Shawe-Taylor, Royal Holloway College (UK) |
| 11H50 | Face identification using support vector machines R. Fernandez, E. Viennet, Univ. Paris 13 (France) |
| Poster session: spotlights | |
| 12H10 | Dimension reduction by local processing C. Wöhler, U. Kressel, J. Schürmann, DaimlerChrysler Res. & Tech., J. Anlauf, Rheinische Friedrich-Wilhelms-Univ. Bonn (Germany) |
| 12H12 | A kernel based adaline T. Friess, R. Harrison, Univ. of Sheffield (UK) |
| 12H14 | Data domain description using support vectors D. Tax, R. Duin, Delft Univ. of Tech. (Netherlands) |
| 12H16 | Support vector machines vs multi-layer perceptrons in particle identification N. Barabino1, M. Pallavicini2, A. Petrolini1,2, M. Pontil1, 3, A. Verri1,3, 1Univ. di Genova, 2Sezione di Genova (Italy), 3MIT (USA) |
| 12H18 | Specialization with cortical models: An application to causality learning H. Frezza-Buet, F. Alexandre, LORIA (France) |
| 12H20 | Generalisation capabilities of a distributed neural classifier A. Ribert, A. Ennaji, Y. Lecourtier, Univ. de Rouen (France) |
| 12H22 | A comparison of three PCA neural techniques S. Fiori, F. Piazza, Univ. of Ancona (Italy) |
| 12H24 | Neural networks which identify composite factors D. MacDonald, D. Charles, C. Fyfe, Univ. of Paisley (Scotland) |
| 12H26 | Supervised Art-II: a new neural network architecture, with quicker learning algorithm, for learning and classifying multivaled input patterns K. R. Al-Rawi, C. Gonzalo, A. Arquero, Univ. Polit. de Madrid (Spain) |
| 12H28 | Poster preview |
| 13H00 | Lunch |
| Special session 8: Support Vector Machines (cont.) | |
| 14H00 | Statistical mechanics of support vector machine A Buhot, M. Gordon, CEA-Grenoble (France) |
| 14H20 | An efficient formulation of sparsity controlled support vector regression P. Drezet, R. Harrison, Univ. of Sheffield (UK) |
| 14H40 | Generalized support vector machines D. Mattera, F. Palmieri, Univ. di Napoli Federico II (Italy), S. Haykin, McMaster Univ. (Canada) |
| 15H00 | Support vector machines for multi-class pattern recognition J. Weston, C. Watkins, Univ. of London (UK) |
| 15H20 | From regression to classification in support vector machines M. Pontil, R. Rifkin, T. Evgeniou, M.I.T. (USA) |
| 15H40 | From first order logic to Nd: a data driven reformulation M. Sebag, Ecole Polytechnique (France) |
| 16H00 | Coffee break |
| Session 9: Classification | |
| 16H20 | Feature binding and relaxation labeling with the competitive layer model H. Wersing, H. Ritter, Univ. of Bielefeld (Germany) |
| 16H40 | Segmentation-free detection of overtaking vehicles with a two-stage time-delay neural network classifier C. Wöhler, J. Schürmann, DaimlerChrysler R&D, J. Anlauf, Rheinische Friedrich-Wilhelms-Univ. (Germany) |
| 17H00 | An integer recurrent artificial neural network for classifying feature vectors R. K. Brouwer, Univ. College of the Cariboo (Canada) |
| 17H20 | Feature selection for ANNs using genetic algorithms in condition monitoring L. Jack, A. Nandi, Univ. of Liverpool (UK) |
| 20H00 | Conference dinner |
| Friday 23rd April 1999 | |
|
Special session 10: Information extraction using unsupervised neural networks |
|
| 9H00 | Trends in Unsupervised Learning C. Fyfe, Univ. of Paisley (UK) |
| 9H20 | Detection of two Gaussian clusters A. Buhot, M. Gordon, CEA-Grenoble (France) |
| 9H40 | Independent component analysis for mixture densities F. Palmieri, A. Budillon, D. Mattera, Univ. di Napoli "Federico II" (Italy) |
| 10H00 | Extraction of intrinsic dimension using CCA - Application to blind sources separation N. Donckers, A. Lendasse, V. Wertz, M. Verleysen, Univ. catholique de Louvain (Belgium) |
| 10H20 | Noise to extract independent causes D. Charles, C. Fyfe, Univ. of Paisley (UK) |
| 10H40 | Coffee break |
| Session 11: ANN models and learning | |
| 11H00 | Orthogonal least square algorithm applied to the initialization of multi-layer perceptrons V. Colla1, L. Reyneri2, M. Sgarbi1, 1Scuola Sup. Sant’Anna, 2Polit. di Torino (Italy) |
| 11H20 | Maximisation of stability ranges for recurrent neural networks subject to on-line adaptation J. Steil, H. Ritter, Univ. of Bielefeld (Germany) |
| 11H40 | Encoding of sequential translators in discrete-time recurrent neural nets R.P. Neco, Univ. Miguel Hernandez, M.L. Forcada, R.C. Carrasco, M.A. Valdez-Munoz, Univ. d’Alacant (Spain) |
| Poster session: spotlights | |
| 12H00 | Information retrieval systems using an associative conceptual space J. van den Berg, Erasmus Univ. Rotterdam, M. Schuemie, Delft Univ. of Technology (The Netherlands) |
| 12H02 | Taking inspiration from the Hippocampus can help solving robotics problems A. Revel, P. Gaussier, J.P. Banquet, Univ. Cergy-Pontoise (France) |
| 12H04 | On the invertibility of the RBF model in a predictive control strategy A. Fache, O. Dubois, A. Billat, Univ. de Reims Champagne-Ardenne (France) |
| 12H06 | Nonlinear factorization in sparsely encoded Hopfield-like neural networks A.M. Sirota, Moscow inst. of Physics and Tech., A.A. Frolov, RAS (Russia), D. Husek, Acad. Sciences (Czech Rep.) |
| 12H08 | Storage capacity and dynamics of nonmonotonic networks B. Crespi, IRST, I. Lazzizzera, Univ. of Trento (Italy) |
| 12H10 | A general approach to construct RBF net-based classifier F. Belloir, A. Fache, A. Billat, Univ. de Reims Champagne-Ardenne (France) |
| 12H12 | Hidden Markov gating for prediction of change points in switching dynamical systems S. Liehr, K. Pawelzik, Univ. of Bremen, J. Kohlmorgen, S. Lemm, K.-R. Müller, GMD FIRST (Germany) |
| 12H14 | Critical and non-critical avalanche behavior in networks of integrate-and-fire neurons C. Eurich, T. Conradi, H. Schwegler, Univ. of Bremen (Germany) |
| 12H16 | Poster preview |
| 13H00 | Lunch |
| Special session 12: Spiking neurons Organised by: Wulfram Gerstner, E.P.F. Lausanne (Switzerland) |
|
| 14H15 | Introduction to spiking neurons W. Gerstner, E.P.F. Lausanne (Switzerland) |
| 14H35 | Fast analog computation in networks of spiking neurons using unreliable synapses T. Natschläger, W. Maass, Tech. Univ. Graz (Austria) |
| 14H55 | Learning a temporal code P. Häfliger, E.T.H. Zürich (Switzerland) |
| 15H15 | VC dimension bounds for networks of spiking neurons M. Schmitt, Ruhr-Univ. Bochum (Germany) |
| 15H35 | What does a neuron talk about ? S. Wilke, C.Eurich, Univ. of Bremen (Germany) |
| 15H55 | Coffee break |
| Session 13: Temporal series | |
| 16H15 | Development of a French speech recognizer using a hybrid HMM/MLP system J.-M. Boite, C. Ris, Fac. Polyt. Mons (Belgium) |
| 16H45 | A hybrid system for fraud detection in mobile communications Y. Moreau, E. Lerouge, H. Verrelst, J. Vandewalle, K.U. Leuven (Belgium), C. Störmann, Siemens Corp. Res. (Germany), P. Burge, Univ. of London (UK) |
| 16H55 | Hybrid HMM/MLP models for times series prediction J. Rynkiewicz, Univ. Paris 1 (France) |