| Wednesday 26 April 2000 | |
| 8H30 | Registration |
| 9H00 | Opening |
| Session 1: Data and signal analysis | |
| 9H10 | A generative model for sparse
discrete binary data with non-uniform categorical priors M. Girolami, Univ. Paisley (Scotland) |
| 9H30 | Using Growing hierarchical self-organizing
maps for document classification M. Dittenbach, D. Merkl, A. Rauber, Vienna Univ. Tech. (Austria) |
| 9H50 | A robust non-linear projection
method J. Lee, A. Lendasse, N. Donckers, M. Verleysen, UCL Louvain-la-Neuve (Belgium) |
| 10H10 | Parametric approach to blind deconvolution
of nonlinear channels J. Sole i Casals1, A. Taleb2, C. Jutten2, 1Univ. Vic (Spain), 2I.N.P. Grenoble (France) |
| 10H30 | Coffee break |
| Special session 2: Support
Vector Machines Organised by: Colin Campbell, Bristol Univ. (UK), Johan Suykens, K.U.Leuven (Belgium) |
|
| 10H50 | Algorithmic approaches to training
Support Vector Machines: a survey C. Campbell, Bristol Univ. (UK) |
| 11H20 | Sparse least squares Support Vector
Machine classifiers J.A.K. Suykens, L. Lukas, J. Vandewalle, K.U.Leuven (Belgium) |
| 11H40 | Support Vector Committee Machines
D. Martinez, LORIA-CNRS, G. Millerioux, CRAN-ESSTIN (France) |
| 12H00 | Robust Bayes Point Machines
R. Herbich, T. Graepel, C. Campbell, TU Berlin (Germany) |
| 12H20 | Lunch |
| Session 3: Model selection and evaluation | |
| 14H00 | A statistical model selection
strategy applied to neural networks J. Pizarro, E. Guerrero, P. L. Galindo, Univ. Cadiz (Spain) |
| 14H20 | Bootstrap for neural model selection
R. Kallel1, M. Cottrell1, V. Vigneron1,2, 1Univ. Paris I, 2Univ. Evry (France) |
| 14H40 | A new information criterion for
the selection of subspace models M. Sugiyama, H. Ogawa, Tokyo Inst. Tech. (Japan) |
| 15H00 | Confidence estimaton methods for
neural networks : a practical comparison G. Papadopoulos, P.J. Edwards, A.F. Murray, Univ. Edinburgh (UK) |
| 15H20 | Coffee break |
| Special session 4: Artificial
neural networks and robotics Organised by: Richard Duro, Jose Santos Reyes, Univ. da Coruna (Spain) |
|
| 15H40 | Using higher order and nodes to
improve sensing capabilities of mobile robots R.J. Duro, J. Santos, J.A. Becerra, F. Bellas, J.L. Crespo, Univ. Coruna (Spain) |
| 16H10 | Competitive neural networks for
robust computation of the optical flow E. Fernandez, I. Echave, M. Grana, UPV-EHU (Spain) |
| 16H30 | Learning VOR-like stabilization
reflexes in robots F. Panerai, G. Metta, G. Sandini, Col. de France (France), Univ. Genova (Italy) |
| 16H50 | Learning of perceptual
states in the design of an adaptive wall-following behaviour M. Fernandez-Delgado, R. Iglesias, S. Barro, Univ. Santiago de Compostela (Spain) |
| Poster session: spotlights | |
| 17H10 | Fuzzy entropy-constrained competitive
learning algorithm W.-J. Hwang, C. Ou, S.-C. Liao, C.-F. Chine, Chung Yuan Christian. Univ. (Taiwan) |
| 17H12 | Specification, estimation and
evaluation of single hidden-layer feedforward autoregressive artificial
neural network models G. Rech, Stockholm Sch. Economics (Sweden) |
| 17H14 | A neural network for undercomplete independent component
analysis L. Wei, J. C. Rajapakse, Nanyang Tech. Univ. (Singapore) |
| 17H16 | Distributed clustering and local
regression for knowledge discovery in multiple spatial databases A. Lazarevic, D. Pokrajac, Z. Obradovic, Washington State Univ. (USA) |
| 17H18 | Nonlinear, statistical data-analysis
for the optimal construction of neural-network inputs with the concept of
a mutual Information F. Heister , G. Schock, DaimlerChrysler Res. Tech. (Germany) |
| 17H20 | Influence of weight-decay training
in input selection methods M. Fernandez-Redondo, C. Hernandez-Espinosa, Univ. Jaume I (Spain) |
| 17H22 | Committee formation for reliable
and accurate neural prediction in industry P.J. Edwards, A.F. Murray, Edinburgh Univ. (UK) |
| 17H24 | Poster preview |
| Thursday 27 April 2000 | |
| Session 5: Non-linear dynamics and control | |
| 9H00 | Toward encryption with neural
network analogy T. Ohira, Sony Comp. Sci. Lab. (Japan) |
| 9H20 | Iterative learning neural network
control for nonlinear system trajectory tracking P. Jiang, R. Unbehauen, Univ. Erlangen-Nürnberg (Germany) |
| 9H40 | A comparative design of a MIMO
neural adaptive rate damping for a nonlinear helicopter model P. A. Gili, M. Battipede, Polit. Torino (Italy) |
| 10H00 | Coffee break |
| Special session 6: Neural networks
in medicine Organised by: Thomas Villmann, Univ. Leipzig (Germany) |
|
| 10H20 | Neural networks approaches in
medicine - a review of actual developments T. Villmann, Univ. Leipzig (Germany) |
| 10H40 | A neural network architecture
for automatic segmentation of fluorescence micrographs T. Nattkemper1, H. Wersing1, W. Schubert2, H. Ritter1, 1Univ. Bielefeld, 2Univ. Magdeburg (Germany) |
| 11H00 | Boundary based movement correction
of functional MR data using a genetic algorithm G. Bao, J. C. Rajapakse, Nanyang Tech. Univ. (Singapore) |
| 11H20 | A neural network approach to adaptive
pattern analysis - the deformable feature map A. Wismüller1, F. Vietze1, D.R. Dersch2, K. Hahn1, H. Ritter3, 1Ludwig-Maximilians-Univ. (Germany), 2Integral Energy Corp. (Australia), 3Univ. Bielefeld (Germany) |
| Poster session: spotlights | |
| 11H40 | Automatic detection of clustered
microcalcifications in digital mammograms using an SVM classifier A. Bazzani1,2, A. Bevilacqua1,2, D. Bollini1,2, R. Brancaccio1,2, R. Carnpanini1,2, N. Lanconelli2, A. Riccardi1,2, D. Romani1,2, G. Zamboni1, 1Univ. Bologna, 2Nat. Ins. Nuclear Physics (Italy) |
| 11H42 | A neuro-fuzzy approach as medical
diagnostic interface R. Brause, F. Friedrich, J.W.Goethe-Univ. (Germany) |
| 11H44 | Regularization in oculomotor control
J. A. Bullinaria, P. M. Riddell, Univ. Reading (UK) |
| 11H46 | Limitations of hybrid systems
B. Hammer, Univ. Osnabrück (Germany) |
| 11H48 | Discriminative learning for neural
decision feedback equalizers E.D. Di Claudio, R. Parisi, G. Orlandi, Univ. Rome "La Sapienza" (Italy) |
| 11H50 | Neurocontrol of a binary distillation
column M.A. Torres1, M.E. Pardo1, J.M. Pupo1, L. Boquete2, R. Barea2, L.M. Bergasa2, 1Univ. Oriente (Cuba), 2Alcala Univ. (Spain) |
| 11H52 | E.O.G. guidance of a weelchair
using spiking neural networks R. Barea, L. Boquete, M. Mazo, E. Lopez, L.M. Bergasa, Univ. Alcala (Spain) |
| 11H54 | Poster preview |
| 12H30 | Lunch |
| Special session 7: Self-organizing
maps for data analysis Organised by: Jouko Lampinen, Kimmo Kaski, Helsinki Univ. of Tech. (Finland) |
|
| 14H00 | Self-Organizing Maps in data analysis
- notes on overfitting and overinterpretation J. Lampinen, T. Kostiainen, Helsinki Univ. Tech. (Finland) |
| 14H20 | Bootstrapping Self-Organizing
Maps to assess the statistical significance of local proximity E. de Bodt1, M. Cottrell2, 1U.C.L. Louvain-la-Neuve (Belgium) & Univ. Lille 2, 2Univ. Paris I (France) |
| 14H40 | Evaluating SOMs using order metrics
A. P. Azcarraga, Nat. Univ. Singapore |
| 15H00 | Self-Organisation in the SOM with
a finite number of possible inputs J.A. Flanagan, Helsinki Univ. Tech. (Finland) |
| 15H20 | Topological map for binary data
M. Lebbah1, F. Badran2, S. Thiria1,2, 1Cons. Nat. Arts Métiers, 2Univ. Paris 6 (France) |
| 15H40 | Analytical comparison of the Temporal
Kohonen Map and the Recurrent Self Organizing Map M. Varsta, J. Heikkonen, J. Lampinen, Helsinki Univ. Tech. (Finland) |
| 16H00 | Coffee break |
| Session 8: Recurrent networks | |
| 16H20 | Local input-output stability of
recurrent networks with time-varying weights J.J. Steil, Univ. Bielefeld (Germany) |
| 16H40 | An optimization neural network
model with time-dependent and lossy dynamics Z. Heszberger, J. Biro, E. Halasz, Tech. Univ. Budapest (Hungary) |
| 17H00 | An algorithm for the addition
of time-delayed connections to recurrent neural networks R. Boné, M. Crucianu, J.-P. Asselin de Beauville, Ec. Ing. Informatique pour l'Industrie (France) |
| Friday 28 April 2000 | |
| Special session 9: Time series
prediction Organised by: Johan Suykens, Joos Vandewalle, K.U.Leuven (Belgium) |
|
| 09H00 | The K.U.Leuven competition data:
a challenge for advanced neural network techniques J.A.K. Suykens, J. Vandewalle, K.U.Leuven (Belgium) |
| 09H10 | Local model optimization for time
series prediction J. McNames, Portland State Univ. (USA) |
| 09H30 | A multi-steap ahead prediction
method based on local dynamic properties G. Bontempi, M. Birattari, ULB Brussels (Belgium) |
| 09H50 | Nonlinear prediction of spatio-temporal
time series U. Parlitz, C. Merkwirth, Univ. Göttingen (Germany) |
| 10H10 | A Bayesian approach to combined
neural networks forecasting M.D. Out, W.A. Kosters, Univ. Leiden (The Netherlands) |
| 10H30 | Coffee break |
| 10H50 | Nonlinear principal component
regression: predicting within the limits of predictability R. Bakker1, J.C. Schouten2, M.-O. Coppens1 ,F. Takens3, C.M. van den Bleek1, 1Delft Univ. Tech., 2Eindhoven Univ., 3Univ. Groningen (The Netherlands) |
| 11H10 | Time series forecasting using
CCA and Kohonen maps - application to electricity consumption A. Lendasse, J. Lee, V. Wertz, M. Verleysen, UCL Louvain-la-Neuve (Belgium) |
| 11H30 | Financial predictions based on
bootstrap-neural networks A. Lombardi1, A. Vicino2, 1Linköping Univ., 2Univ. Siena (Italy) |
| 11H50 | On the use of the wavelet decomposition
for time series prediction S. Soltani, Univ. Tech. Compiègne (France) |
| Poster session: spotlights | |
| 12H10 | Chaotic time series prediction
using the Kohonen algorithm L. Monzon Benitez1,2, A. Ferreira1, D. I. Pedreira2, 1Univ. Sao Paulo (Brazil), 2Univ. Medica Carlos J. Finlay (Cuba) |
| 12H12 | Curve forecast with the SOM algorithm:
using a tool to follow the time on a Kohonen map P. Rousset, Univ. Paris I (France) |
| 12H14 | Learning principal components
in a contextual space T. Voegtlin, Inst. Sci. Cognitives (France) |
| 12H16 | Training activation function in
parametric classification V. Colla1, L.M. Reyneri2, M. Sgarbi1, 1Sc. Sup. Sant'Anna, 2Polit. Torino (Italy) |
| 12H18 | Quantum iterative algorithm for
image reconstruction problems J.-I. Inoue, Tokyo Inst. Tech. (Japan) |
| 12H20 | Quaternionic spinor MLP S. Buchholz, G. Sommer, Univ. Kiel (Germany) |
| 12H22 | Simplified neural architectures
for symmetric boolean functions B. Girau, McGill Univ. (USA) & INRIA (France) |
| 12H24 | Poster preview |
| 13H00 | Lunch |
| Special session
10: Artificial neural networks for energy management systems Organised by: Gonzalo Joya, Univ. de Malaga (Spain) |
|
| 14H15 | Connectionist solutions for energy
management systems G. Joya, Univ. Malaga (Spain) |
| 14H55 | Stability assessment of electric
power systems using growing neural gas and self-organizing maps C. Rehtanz, C. Leder, Univ. Dortmund (Germany) |
| 15H15 | DMS feeder load forecasting dealing
with MV network reconfiguration J.N. Fidalgo, J.A. Pecas Lopes, INESC (Portugal) |
| 15H35 | Appication of MLP and stochastic
simulations for electricity load forecasting in Russia E. Savelieva1, A. Kravetski1, S. Chernov1, V. Demyanov1, V. Timonin1, R. Arutyunyan1, L. Bolshov1, M. Kanevski1,2, 1Nuclear Safety Inst. (Russia), 2IDIAP (Switzerland) |
| 15H55 | Coffee break |
| Session 11: Learning in biological and artificial systems | |
| 16H10 | SpikeProp: backpropagation for
networks of spiking neurons S. M. Bohte1, J. N. Kok2, H. La Poutré1, 1CWI, 2Leiden Univ. (the Netherlands) |
| 16H30 | Nonsynaptically connected neural
nets G. L. Aiello1,2, P. Bach-y-Rita1, 1Univ. Wisconsin-Madison (USA), 2Univ. Palermo (Italy) |
| 16H50 | Establishing retinotopy by lateral-inhibition
type homogeneous neural fields W. A. Fellenz, J. G. Taylor, King's Coll. (UK) |