| Wednesday 24 April 2002 | |
| 8H30 | Registration |
| 9H00 | Opening |
| Session 1: Regression | |
| 9H10 | Efficient formation of a basis in a kernel induced feature space |
| G.C. Cawley, N.L.C. Talbot, Univ. East Anglia (UK) | |
| 9H30 | Theoretical properties of functional Multi Layer Perceptrons |
| F. Rossi*, B. Conan-Guez, F. Fleuret, INRIA, *Univ. Paris 9 (France) | |
| 9H50 | Storing many-to-many mappings on a feed-forward neural network using fuzzy sets |
| R.K. Brouwer, Univ. College Cariboo (Canada) | |
| 10H10 | Heteroscedastic regularised kernel regression for prediction of episodes of poor air quality |
| R.J. Foxall, G.C. Cawley, N.L.C. Talbot, S.R. Dorling, D.P. Mandic, Univ. East Anglia (UK) | |
| 10H30 | Coffee break |
| Special session 2: Exploratory Data Analysis in Medicine and Bioinformatics | |
| Organised by A. Wismüller, Ludwig-Maximilians-Univ. München, T. Villmann, Univ. Leipzig (Germany) | |
| 11H00 | Exploratory Data Analysis in Medicine and Bioinformatics |
| A. Wismüller*, T. Villmann, Univ. Leipzig, * Ludwig-Maximilians-Univ. München (Germany) | |
| 11H20 | A data visualisation method for investigating the reliability of a high-dimensional low-back-pain MLP network |
| M.L. Vaughn*, S.J. Taylor, M.A. Foy, A.J.B. Fogg, Princess Margaret Hospital, *Cranfield Univ. (UK) | |
| 11H40 | Learning classification rules from electroencephalograms |
| V. Schetinin, J. Schult, Univ. Jena (Germany) | |
| 12H00 | Double self-organizing maps to cluster gene expression data |
| D. Wang, H. Ressom, M.T. Musavi, C. Domnisoru, Univ. Maine (USA) | |
| 12H20 | Lunch |
| Session 3: Sampling and model selection | |
| 13H50 | Nonparametric importance sampling for Bayesian inference |
| M. Zlochin, Y. Baram, Israel Inst. Tech. (Israel) | |
| 14H10 | Parametric bootstrap for asymptotic test of contrast difference in neural networks |
| R. Kallel, J. Rynkiewicz, Univ. Paris 1 (France) | |
| 14H30 | A stepwise statistical methodology for determining the size of a neural network |
| A. Yanez Escolano, E. Guerrero Vazquez, P.L. Galindo Riano, J. Pizarro Junquera, Univ. Cadiz (Spain) | |
| 14H50 | Coffee break |
| Special session 4: Neural Networks and Cognitive Science | |
| Organised by H. Paugam-Moisy, Univ. Lyon2, D. Puzenat, Univ. Antilles-Guyane (France) | |
| 15H20 | Neural networks for modelling memory : case studies |
| Hélène Paugam-Moisy, Didier Puzenat, Emanuelle Reynaud, Jean-Philippe Magué, Inst. Sciences Cognitives, Bron (France) | |
| 16H00 | Connectionist models investigating representations formed in the sequential generation of characters |
| F.M. Richardson, N. Davey, L. Peters, D.J. Done, S.H. Anthony, Univ. Hertfordshire (UK) | |
| 16H20 | The problem of adaptive control in a living system or how to acquire an inverse model without the help of an external teacher |
| K. Th. Kalveram, T. Schinauer, Heinrich-Heine-Univ. (Germany) | |
| Poster session: spotlights | |
| Special session 4 | |
| 16H40 | Biologically-inspired human motion detection |
| V. Laxmi, J.N. Carter, R.I. Damper, Univ. Southampton (UK) | |
| 16H42 | Why will rat's go where rats will not? |
| J. Hayes, V. Murphy, N. Davey, P. Smith, L. Peters, Univ. Hertfordshire (UK) | |
| Special session 2 | |
| 16H44 | Improving robustness of fuzzy gene modeling |
| R. Reynolds, H. Ressom, M. Musavi, C. Domnisoru, Univ. Maine (USA) | |
| Regular Session | |
| 16H46 | Rule extraction from support vector machines |
| H. Nunez**, C. Angulo*, A. Catala*, Univ. Catalonia, *LEA-SICA (Spain), **Univ. Central (Venezuela) | |
| 16H48 | Fuzzy support vector machines for multiclass problems |
| S. Abe, T. Inoue, Kobe Univ. (Japan) | |
| 16H50 | Different criteria for active learning in neural networks: a comparative study |
| J. Poland, A. Zell, Univ. Tübingen (Germany) | |
| 16H52 | Supervised learning in committee machines by PCA |
| C. Bunzmann, M. Biehl, R. Urbanczik, Univ. Würzburg (Germany) | |
| 16H54 | The use of LS-SVM in the classification of brain tumors based on Magnetic Resonance Spectroscopy signals |
| L. Lukas, A. Devos, J.A.K. Suykens, L. Vanhamme, S. Van Huffel, A.R. Tate*, C. Majos**, C. Arus***, K.U.Leuven (Belgium), *St. George's Hospital (UK), **IDI, ***Univ. Aut. Barcelona (Spain) | |
| 16H56 | Clustering in data space and feature space |
| D. MacDonald, C. Fyfe, Univ. Paisley (Scotland) | |
| 16H58 | Maximum likelihood Hebbian rules |
| C. Fyfe, E. Corchado, Univ. Paisley (Scotland) | |
| 17H00 | Fast exact leave-one-out cross-validation of least-squares Support Vector Machines |
| K. Saadi, G.C. Cawley, N.L.C. Talbot, Univ. East Anglia (UK) | |
| 17H02 | Noise derived information criterion for model selection |
| J. Pizarro, P. Galindo, E. Guerrero, A. Yanez, Univ. Cadiz (Spain) | |
| 17H04 | An unified framework for 'All data at once' multi-class Support Vector Machines |
| C. Angulo, X. Parra, A. Catala, Tech. Univ. Catalonia (Spain) | |
| 17H06 | Prediction of mental development of preterm newborns at birth time using LS-SVM |
| L. Ameye, C. Lu, L. Lukas, J. De Brabanter, J.A.K. Suykens, S. Van Huffel, H. Daniels, G. Naulaers, H. Devlieger, K.U. Leuven (Belgium) | |
| 17H08 | Poster preview |
|
|
|
| Thursday 25 April 2002 | |
| Special session 5: Representation of high-dimensional data | |
| Organised by A. Guérin-Dugué, CLIPS, and J. Hérault, LIS Grenoble (France) | |
| 09H00 | Searching for the embedded manifolds in high-dimensional data, problems and unsolved questions |
| J. Hérault, Anne Guérin-Dugué*, Pierre Villemain, LIS Grenoble, * CLIPS Grenoble (France) | |
| 09H40 | Curvilinear Distance Analysis versus Isomap |
| J.A. Lee, A. Lendasse, M. Verleysen, Univ. cat. Louvain (Belgium) | |
| 10H00 | Fast nonlinear dimensionality reduction with topology representing networks |
| J.J. Verbeek, N. Vlassis, B. Krose, Univ. Amsterdam (Netherlands) | |
| 10H20 | When does geodesic distance recover the true hidden parametrization of families of articulated images? |
| D. Donoho, C. Grimes, Stanford Univ. (USA) | |
| 10H40 | How to generalize geometric ICA to higher dimensions |
| F.J. Theis, E.W. Lang, Univ. Regensburg (Germany) | |
| Poster session: spotlights | |
| Special session 5 | |
| 11H00 | Neural dimensionality reduction for document processing |
| M. Delichère*, D. Memmi, IMAG Grenoble, *Amoweba Annecy (France) | |
| Regular Session | |
| 11H02 | Geometric overcomplete ICA |
| F.J. Theis, E.W. Lang, Univ. Regensburg (Germany) | |
| 11H04 | Advantages and drawbacks of the Batch Kohonen algorithm |
| J.-C. Fort*, P. Letremy, M. Cottrell, Univ. Paris I, *Univ. Nancy I (France) | |
| 11H06 | Mobile radio access network monitoring using the self-organizing map |
| P. Lehtimäki, K. Raivio, O. Simula, Helsinki Univ. Tech. (Finland) | |
| 11H08 | Evaluating the impact of multiplicative input perturbations on radial basis function networks |
| J.L. Bernier, J. Gonzales, A. Canas, A.F. Diaz, F.J. Fernandez, J. Ortega, Univ. Granada (Spain) | |
| 11H10 | Learning sparse representations of three-dimensional objects |
| G. Peters*, C. von der Malsburg, Ruhr-Univ. Bochum, *Univ. Dortmund (Germany) | |
| 11H12 | An estimation model of pupil size for 'Blink Artifact' and it's applications |
| M. Nakayama*, Y. Shimizu, Nat. Inst. Educational Policy Res., *Tokyo Inst. Tech (Japan) | |
| 11H14 | Novelty detection for strain-gauge degradation using maximally correlated components |
| G. Hollier, J. Austin, Univ. York (UK) | |
| 11H16 | Modeling efficient conjunction detection with spiking neural networks |
| S.M. Bohte, J.N. Kok*, H. La Poutré**, CWI, *Leiden Univ., **TU Eindhoven (Netherlands) | |
| 11H18 | Segmental duration control by time delay neural networks with asymmetric causal and retro-causal information flows |
| C. Erden, H.G. Zimmermann, Siemens AG (Germany) | |
| 11H20 | Neural predictive coding for speech discriminant feature extraction: The DFE-NPC |
| M. Chetouani, B. Gas, J.L. Zarader, C. Chavy, Univ. Paris VI (France) | |
| 11H22 | Multiresolution codes for scene categorization |
| N. Denquive, P. Tarroux*, CNRS, *ENS (France) | |
| 11H24 | Evaluation of gradient descent learning algorithms with adaptive and local learning rate for recognising hand-written numerals |
| M. Giudici, F. Queirolo, M. Valle, Univ. Genova (Italy) | |
| 11H26 | Poster preview and coffee break |
| 12H15 | Lunch |
| Session 6: Learning | |
| 13H45 | Batch-RLVQ |
| B. Hammer*, T. Villmann, Univ. Leipzig, *Univ. Osnabrück (Germany) | |
| 14H05 | Combining gestural and contact information for visual guidance of multi-finger grasps |
| G. Heidemann, H. Ritter, Univ. Bielefeld (Germany) | |
| 14H25 | Separation of a mixture of signals using linear filtering and second order statistics |
| A.M. Tomé, Univ. Aveiro (Portugal) | |
| 14H45 | Sparse image coding using an asynchronous spiking neural network |
| L. Perrinet, M. Samuelides, Univ. Paul Sabatier (France) | |
| 15H05 | Coffee break |
| Special session 7: Hardware and Parallel Computer Implementations of Neural Networks | |
| Organised by U. Seiffert, Univ. Magdeburg (Germany) | |
| 15H30 | Artificial Neural Networks on Massively Parallel Computer Hardware |
| U. Seiffert, Univ. Magdeburg (Germany) | |
| 16H00 | PCNN neurocomputers - Event driven and parallel architectures |
| C. Grassmann, T. Schoenauer, C. Wolff, Infineon Technologies (Germany) | |
| 16H20 | A reconfigurable SOM hardware accelerator |
| M. Porrmann, M. Franzmeier, H. Kalte, U. Witkowski, U. Rückert, Univ. Paderborn (Germany) | |
| 16H40 | Stochastic resonance and finite resolutions in a leaky integrate-and-fire neuron |
| N. Mtetwa, L.S. Smith, A. Hussain, Univ. Stirling (Scotland) | |
| 17H00 | Hardware solutions for implementation of neural networks in High Energy Physics triggers |
| J.-C. Prévotet, B. Denby, P. Garda, B. Granado, C. Kiesling, Univ. Paris VI (France) | |
|
|
|
| Friday 26 April 2002 | |
| Special session 8: Perspectives on Learning with Recurrent Networks | |
| Organised by B. Hammer, Univ. Osnabrück, J.J. Steil, Univ. Bielefeld (Germany) | |
| 09H00 | Perspectives on learning with recurrent neural networks |
| B. Hammer*, J.J. Steil, Univ. Bielefeld, * Univ. Osnabrück (Germany) | |
| 09H30 | DEKF-LSTM |
| F.A. Gers*, J.A. Perez-Ortiz**, D. Eck, J. Schmidhuber, IDSIA (Switzerland), *Mantik Bioinformatik, Berlin (Germany), **Univ. Alacant (Spain) | |
| 09H50 | Generalization by structural properties from sparse nested symbolic data |
| M. Boden, Halmstad Univ. (Sweden) | |
| 10H10 | Estimating probabilities for unbounded categorization problems |
| J. Henderson, Univ. Geneva (Switzerland) | |
| 10H30 | A general framework for unsupervised processing of structured data |
| B. Hammer*, A. Micheli, A. Sperduti, Univ. Pisa (Italy), *Univ. Osnabrück (Germany) | |
| Poster session: spotlights | |
| Special session 8 | |
| 10H50 | Undershooting: modeling dynamical systems by time grid refinements |
| H.G. Zimmermann, R. Neuneier, R. Grothmann, Siemens AG Munich (Germany) | |
| 10H52 | Learning in a chaotic neural network |
| N. Crook, T. olde Scheper, Oxford Brookes Univ. (UK) | |
| 10H54 | Yield curve forecasting by error correction neural networks and partial learning |
| H.G. Zimmermann, Ch. Tietz, R. Grothmann, Siemens AG Munich (Germany) | |
| 10H56 | Extended Kalman Filter trained Recurrent Radial Basis Function Network in Nonlinear System Identification |
| B. Todorovic*, M. Stankovic*, C. Moraga, Univ. Dortmund (Germany), *Univ. Nis (Yugoslavia) | |
| Regular Session | |
| 10H58 | State reconstruction of piecewise linear maps using a clustering machine |
| G. Millerioux, G. Bloch, Centre Rech. Automatique Nancy (France) | |
| 11H00 | Unsupervised classifier for monitoring and diagnostic of time series |
| S. Lecoeuche, USTL & EIPC (France) | |
| 11H02 | Width optimization of the Gaussian kernels in Radial Basis Function Networks |
| N. Benoudjit, C. Archambeau, A. Lendasse, J. Lee, M. Verleysen, Univ. cat Louvain (Belgium) | |
| 11H04 | High frequency forecasting with associative memories |
| A. Pasley, J. Austin, Univ. York (UK) | |
| 11H06 | Nonlinear PCA: a new hierarchical approach |
| M. Scholz, R. Vigario*, Fraunhofer Inst. (Germany), *NN Research Centre (Finland) | |
| 11H08 | Probabilistic derivation and Multiple Canonical Correlation Analysis |
| P.L. Lai, York Univ. (UK) | |
| 11H10 | Orthogonal transformations for optimal time series prediction |
| M. Salmeron, A. Prieto, J. Ortega, C.G. Puntonet, M. Rodriguez Alvarez, Univ. Granada (Spain) | |
| 11H12 | Neuro-fuzzy methodologies for the clustering and the reliability estimation of olive fruit fly infestation |
| E. Bellei, R. Petacchi*, L. Reyneri, Polit. Torino, *Scuola Sup. S. Anna Pisa (Italy) | |
| 11H14 | Use of artificial neural networks process analyzers: a case study |
| H. Al-Duwaish, L. Ghouti, T. Halawani, M. Mohandes, King Fahd Univ. of Petroleum and Minerals (Saudi Arabia) | |
| 11H16 | Poster preview and coffee break |
| Session 9: Information extraction | |
| 12H00 | Forecasting using twinned principal curves |
| Y. Han, C. Fyfe, Univ. Paisley (Scotland) | |
| 12H20 | Kernel Temporal Component Analysis |
| D. Martinez, A. Bray, LORIA-CNRS (France) | |
| 12H40 | Exploratory Correlation Analysis |
| J. Koetsier, D. MacDonald, D. Charles, C. Fyfe, Univ. Paisley (Scotland) | |
| 13H00 | Lunch |
| Special session 10: Neural Network Techniques in Fault Detection and Isolation | |
| Organised by S. Simani, Univ. Ferrara (Italy) | |
| 14H15 | Neural networks for fault diagnosis and identification of industrial processes |
| S. Simani, C. Fantuzzi, Univ. Ferrara (Italy) | |
| 14H55 | Neural networks for fault diagnosis of industrial plants at different working points |
| S. Simani*, R. J. Patton, Univ. Hull (UK), *Univ. Ferrara (Italy) | |
| 15H15 | Fault diagnosis of an electro-pneumatic valve actuator using neural networks with fuzzy capabilities |
| F.J. Uppal, R.J. Patton, Univ. Hull (UK) | |
| 15H35 | Non-linear Canonical Correlation Analysis using a RBF networks |
| S. Kumar, E.B. Martin, J. Morris, Univ. Newcastle (UK) | |
| 15H55 | Free-swinging and locked joint fault detection and isolation in cooperative manipulators |
| R. Tinos, M. H. Terra, Univ. Sao Paulo (Brazil) | |
| 16H25 | Coffee break - end of conference |