Wednesday 23 April 2003 | |
8H30 | Registration |
9H00 | Opening |
Special session 1: Links between neural networks and webs | |
Organised by Marco Gori, Univ. Siena (Italy) | |
9H00 | A general framework for learning in web domains |
M. Gori, Univ. Siena (Italy) | |
9H40 | Subject Categorization for Web Educational Resources using MLP |
M. Nakayama, Tokyo Inst. Tech., Y. Shimizu, Nat. Inst. Educational Policy Research (Japan) | |
10H00 | Model growing networks with directional attachment and communities |
M. Kimura, K. Saito, N. Ueda, NTT Communication Science Lab. (Japan) | |
10H20 | Coffee break |
Session 2: Self-organization and topology representation | |
10H40 | High-dimensional labeled data analysis with Gabriel graphs |
M. Aupetit, CEA (France) | |
11H00 | Unsupervised Recursive Sequence Processing |
M. Strickert, B. Hammer, Univ. Osnabrück (Germany) | |
11H20 | Neural networks organizations to learn complex robotic functions |
G. Hermann, P. Wira, J-P. Urban, Univ. Mulhouse (France) | |
11H40 | Self-organizing maps and functional networks for local dynamic modeling |
N. Sánchez-Maroño, O. Fontenla Romero, A. Alonso-Betanzos, B. Guijarro-Berdiñas, Univ. A Coruna (Spain) | |
12H00 | Robust Topology Representing Networks |
M. Aupetit, CEA (France) | |
12H20 | A New Efficient Alternative to Asymmetric SOM and MDS Algorithms |
A. Muñoz, M. Martin-Merino, Univ. Carlos III Madrid (Spain) | |
12H40 | Lunch |
Special session 3: Mathematical aspects of neural networks | |
Organised by Barbara Hammer, Univ. Osnabrück (Germany), Thomas Villmann, Univ. Leipzig (Germany) | |
14H20 | Mathematical Aspects of Neural Networks |
B. Hammer, Univ. Osnabrück, T. Villmann, Univ. Leipzig (Germany) | |
14H50 | On the weight dynamics of recurrent learning |
U. D. Schiller, J. J. Steil, Bielefeld Univ. (Germany) | |
15H10 | A Neural Graph Isomorphism Algorithm based on local Invariants |
B.J. Jain, F. Wysotzki, TU Berlin (Germany) | |
15H30 | Analyzing Qualitative variables using the Kohonen algorithm |
M. Cottrell, P. Letrémy, Univ. Paris1 (France) | |
15H50 | Magnification Control in Winner Relaxing Neural Gas |
J. C. Claussen, Christian-Albrecht-Univ. Kiel, T. Villmann, Univ. Leipzig (Germany) | |
Poster session: spotlights | |
Special session 3 | |
16H10 | On Convergence Problems of the EM Algorithm for Finite Gaussian Mixtures |
C. Archambeau, J. A. Lee, M. Verleysen, Univ. cat. Louvain (Belgium) | |
16H11 | An Associative Memory for the Automorphism Group of Structures |
B.J. Jain, F. Wysotzki, TU Berlin (Germany) | |
16H12 | Approximation of Function by Adaptively Growing Radial Basis Function Neural Networks |
Li Jianyu*,**, Luo Siwei*, Qi Yingjian*, *Northern Jiaotong Univ., **Beijing Broadcasting Inst. (P.R. China) | |
Regular Session | |
16H13 | Cellular topographic self-organization under correlational learning |
S. Sakamoto*, S. Seki**, Y. Kobuchi*, *Ryukoku Univ. (Japan), **California State Univ. (USA) | |
16H14 | Self-Organization by Optimizing Free-Energy |
J.J. Verbeek, N. Vlassis, B. Krose, Univ. Amsterdam (The Netherlands) | |
16H15 | Comparison of neural algorithms for blind source separation in sensor array applications |
G. Bedoya, S. Bermejo, J. Cabestany, Tech. Univ. Catalonia (Spain) | |
16H16 | Neural Net with Two Hidden Layers for Nonlinear Blind Source Separation |
R. Martin-Clemente, S. Hornillo-Mellado, J. I. Acha, Univ. Sevilla, C. G. Puntonet, Univ. Granada (Spain) | |
16H17 | Acceptability conditions for BSS problems |
V. Vigneron*,**, S. Lagrange**, C. Jutten**, *Univ. Paris 1, **INPG (France) |
|
16H18 | Extraction of fuzzy rules from trained neural network using evolutionary algorithm |
U. Markowska-Kaczmar, W. Trelak, Wroclaw Univ. Tech. (Poland) | |
16H19 | A new rule extraction algorithm based on interval arithmetic |
C. Hernandez-Espinosa, M. Fernandez-Redondo, M. Ortiz-Gomez, Univ. Jaume I (Spain) | |
16H20 | Searching optimal feature subset using mutual information |
D. Huang, T.W.S. Chow, City University (Hong Kong) | |
16H21 | Statistical downscaling with artificial neural networks |
G. C. Cawley, M. Haylock, S. R. Dorling, C. Goodess, P. D. Jones, Univ. East Anglia (UK) | |
16H22 | Online Identification and Control of a PV-Supplied DC Motor Using Universal Learning Networks |
A. Hussein*, K. Hirasawa**, J. Hu*, J. Murata*, *Kyushu Univ., **Waseda Univ. (Japan) | |
16H23 | On radial basis function network equalization in the GSM system |
A. Kantsila, M. Lehtokangas, J. Saarinen, Tampere Univ. Tech. (Finland) | |
16H25 | Coffee break and poster preview |
|
|
Thursday 24 April 2003 | |
Special session 4: New directions in support vector machines and kernel based learning | |
Organised by Massimiliano Pontil, Univ. Siena (Italy), Johan Suykens, K.U. Leuven (Belgium) | |
09H00 | An introduction to support vector machines and kernel based methods |
J. Suykens, K.U. Leuven (Belgium) | |
09H30 | In different ensembles of kernel machines |
M. Yamana*, H. Nakahara*, M. Pontil**, S. Amari*, *RIKEN (Japan), **Univ. of Siena (Italy) | |
09H50 | Kernel PLS variants for regression |
L. Hoegaerts, J.A.K. Suykens, J. Vandewalle, B. De Moor, K.U. Leuven (Belgium) | |
10H10 | Unbiased estimation of conditional variance in heteroscedastic kernal ridge regression |
G.C. Cawley, N.L.C. Talbot, R.J. Foxall, S.R. Dorling, Univ. East Anglia, D.P. Mandic, Imperial College (UK) | |
10H30 | On the equality of kernel AdaTron and sequential minimal optimization in classification and regression tasks and alike algorithms for kernel machines |
V. Kecman*, M. Vogt**, T.M. Huang*, *Univ. Auckland (New Zealand), **TU Darmstadt (Germany) | |
10H50 | Finding clusters using support vector classifiers |
K. Jong, E. Marchiori, A. van der Vaart, Free Univ. Amsterdam (The Netherlands) | |
Poster session: spotlights | |
Special session 4 | |
11H10 | Classification of handwritten digits using supervised locally linear embedding algorithm and support vector machine |
O. Kouropteva, O. Okun, M. Pietikäinen, Univ. Oulu (Finland) | |
11H11 | Improving iterative repair strategies for scheduling with the SVM |
K. Gersmann, B. Hammer, Univ. Osnabrück (Germany) | |
11H12 | Efficient cross-validation of kernel fisher discriminant classifiers |
G. C. Cawley, N. L. C. Talbot, Univ. East Anglia (UK) | |
Regular Session | |
11H13 | RetinotopicNET: An Efficient Simulator for Retinotopic Visual Architectures |
R. C. Muresan, Cluj-Napoca (Romania) | |
11H14 | Accelerating the convergence speed of neural networks learning methods using least squares |
O. Fontenla-Romero*, D. Erdogmus**, J. C. Principe**, A. Alonso-Betanzos*, E. Castillo***, *Univ. A Coruna, ***Univ. Castilla-La Mancha (Spain), **Univ. Florida (USA) | |
11H15 | Ensemble Methods for Multilayer Feedforward |
C. Hernandez-Espinosa, M. Fernandez-Redondo, M. Ortiz-Gomez, Univ. JaumeI (Spain) | |
11H16 | Robust Vector Quantization for Burst Error Channels Using Genetic Algorithm |
W.-J. Hwang : C.-M. Ou : C.-M. Yeh, Chung Yuan Christ. Univ. (Taiwan) | |
11H17 | Neural coding model using the morphoelectrotonic transform theory |
N. Watanabe, S.Ishizaki, Keio Univ. (Japan) | |
11H18 | Neural assembly binding in linguistic representation |
F. van der Velde, M. de Kamps, Univ. Leiden (The Netherlands) | |
11H19 | Developmental pruning of synapses and category learning |
R. Viviani, M. Spitzer, Universitätsklinikum Ulm (Germany) | |
11H20 | An event driven framework for the simulation of networks of spiking neurons |
O. Rochel, D. Martinez, LORIA (France) | |
11H21 | Road Singularities Detection and Classification |
A.P. Leitao, S. Tilie, M. Mangeas, J.-P. Tarel, LIVIC, V. Vigneron, S. Lelandais, Univ. Evry (France) | |
11H22 | Characterization of the absolutely expedient learning algorithms for stochastic automata in a non-discrete space of actions |
C. Rivero, Univ. Complutense Madrid (Spain) | |
11H25 | Coffee break and poster preview |
12H30 | Lunch |
Session 5: Biologically plausible learning | |
14H00 | A model-based reinforcement learning: a computational model and an fMRI study |
W. Yoshida. S. Ishii, Nara Inst. Science Tech. (Japan) | |
14H20 | A neural model for heading detection from optic flow |
F. Seifart, P. Bayerl, H. Neumann, Univ. Ulm (Germany) | |
14H40 | Parallel asynchronous distributed computations of optimal control in large state space Markov Decision processes |
B. Scherrer, LORIA (France) | |
Session 6: Mixtures and ensemble learning | |
15H00 | Mixture of Experts and Local-Global Neural Networks |
M. S. Fariñas, C. E. Pedreira, Cat. Univ. Rio de Janeiro (Brazil) | |
15H20 | Ensemble of hybrid networks with strong regularization |
S. Cohen, N. Intrator, Tel Aviv Univ. (Israel) | |
15H40 | A new MetaMachine Learning (MML) method based on combining non-significant different neural networks |
A. Yáñez Escolano, J. Pizarro Junquera, E. Guerrero Vázquez, P. Galindo Riaño, Univ. Cadiz (Spain) | |
16H00 | Coffee break |
Session 7: Classification | |
16H20 | Applying Scaled Conjugate Gradient for the Classification of Infant Cry with Neural Networks |
J. Orozco, C. A. Reyes, INAOE (Mexico) | |
16H40 | 1-v-1 Tri-Class SV Machine |
C. Angulo, Unic. Polit. Catalunya, L. González, Univ. Seville (Spain) | |
17H00 | A Spiking Machine for Human-Computer Interactions |
G. Vaucher, Supélec (France) | |
17H20 | A Fuzzy ARTMAP Probability Estimator with Relevance Factor |
R. Andonie, L. Sasu, Transylvania Univ. (Romania) | |
|
|
Friday 25 April 2003 | |
Session 8: Dynamical systems and recurrent networks | |
09H00 | Anticipating the response of excitable system driven by random forcing |
M. Ciszak*, O. Calvo*, C. Masoller*,**, C. R. Mirasso*, R. Toral*, *Univ. Illes Balears (Spain), **Univ. Republica (Uruguay) | |
09H20 | Autonomous learning algorithm for fully connected recurrent networks |
E. leclercq, F. Druaux, D. Lefebvre, Univ. du Havre (France) | |
09H40 | Neural Network Algorithms for the p-Median Problem |
E. Dominguez Merino, J. Muñoz Perez, J. Jerez Aragones, Univ. Malaga (Spain) | |
Special session 9: Industrial and agronomical applications of neural networks | |
Organised by Leonardo M. Reyneri, Politecnico di Torino (Italy) | |
10H00 | On industrial acceptance of neural and fuzzy systems |
L. M. Reyneri, Politecnico di Torino (Italy) | |
10H20 | Comparison of traditional and neural systems for train speed estimation |
V. Colla, M. Vannucci, Scuola Superiore Sant'Anna, B. Allotta, M. Malvezzi, Univ. Firenze (Italy) | |
10H40 | Neural Networks and M5 model trees in modeling water level-discharge relationship for an Indian river |
B. Bhattacharya, D.P. Solomatine, IHE Delft (The Netherlands) | |
11H00 | Post-Failure Analysis of an adaptive predictor-corrector neural controller on an F-15 flight simulator |
M. Battipede, P. Gili, M. Lando, L. Massotti, Polit. Torino (Italy), M.R. Napolitano, M.G. Perhinschi, West Virginia Univ. (USA) | |
Poster session: spotlights | |
Special session 9 | |
11H20 | Statistical and Neural Network Forecasts of Apparel Sales |
L.M. Sztandera, C. Frank, A. Garg, Philadelphia Univ., A. Raheja, California State Polyt. (USA) | |
Regular Session | |
11H21 | An Analysis of Synchrony Conditions for Integrate-and-Fire Neurons |
D. Kim, Max Planck Inst. Psychological Res. (Germany) | |
11H22 | Stimulation of peripheral nerves for restoration of handfunction of quadriplegic patients using an artificial neural net based controller |
M. Bogdan, M. Schröder, W. Rosenstiel, Univ Tübingen (Germany) | |
11H23 | Monitoring technical systems with prototype based clustering |
T. Bojer*, B. Hammer**, C. Koers*, *Prognost Systems, **Univ. Osnabrück (Germany) | |
11H24 | Evolved Neurodynamics for Robot Control |
F. Pasemann, M. Hülse, K. Zahedi, Fraunhofer Inst. Autonomous Intelligent Systems (Germany) | |
11H25 | VLSI Realization of a Two-Dimensional Hamming Distance Comparator ANN for Image Processing Applications |
S. Badel, A. Schmid, Y. Leblebici, EPFL (Switzerland) | |
11H26 | Recursive Least Squares for an Entropy Regularized MSE Cost Function |
D. Erdogmus, Y. N. Rao, J. C. Principe, Univ. Florida (USA), O. Fontenla-Romero, A. Alonso-Betanzos, Univ. A Coruna (Spain) | |
11H27 | A view-based approach for object detection in image sequences |
A. Zehender, P. Bayerl, H. Neumann, Univ. Ulm (Germany) | |
11H28 | Extracting Interface Assertions from Neural Networks in Polyhedral Format |
S.Breutel, F.Maire, R. Hayward, Queensland Univ. Tech. (Australia) | |
11H29 | The hypersphere neuron |
V. Banarer, C. Perwass, G. Sommer, CAU Kiel (Germany) | |
11H30 | Fast approximation of the bootstrap for model selection |
G. Simon, A. Lendasse, V. Wertz, M. Verleysen, Univ. cat. Louvain (Belgium) | |
11H31 | Associative morphological memories for spectral unmixing |
M. Grana, J. Gallego, UPV/EHU (Spain) | |
11H32 | Adaptive Learning in Changing Environments |
M. Rocha, P. Cortez, J. Neves, Univ. Minho (Portugal) | |
11H35 | Coffee break and poster preview |
12H30 | Lunch |
Special session 10: Digital image processing with neural networks | |
Organised by Axel Wismüller, Univ. Munich (Germany), Udo Seiffert, IPK Gatersleben (Germany) | |
14H00 | Digital Image Processing with Neural Networks |
A. Wismüller, Univ. Munich (Germany), U. Seiffert, IPK Gatersleben (Germany) | |
14H20 | Semi-automatic acquisition and labelling of image data using SOMs |
G. Heidemann, A. Saalbach, H. Ritter, Univ. Bielefeld (Germany) | |
14H40 | Model-Free Functional MRI Analysis Using Topographic Independent Component Analysis |
A. Meyer-Baese, T.D. Otto, Florida State Univ. (USA), T. Martinetz, Luebeck Univ., D. Auer, Max Planck Inst. Psychiatry, A. Wismüller, Univ. Munich (Germany) | |
15H00 | Neural Network Performances in Astronomical Image Processing |
R. Cancelliere, M. Gai, Univ. Torino (Italy) | |
15H20 | Coffee break |
15H40 | A recognition of filaments in solar images with an artificial neural network |
V.V. Zharkova, Univ. Bradford, V. Schetinin, Univ. Exeter (UK) | |
16H00 | Locally Linear Embedding versus Isotop |
J.A. Lee, C. Archambeau, M. Verleysen, Univ. cat. Louvain (Belgium) | |
16H20 | Meter value recognition using locally connected hierarchical networks |
S. Behnke, Intl. Computer Science Inst. (USA) | |
16H40 | End of conference |