| Wednesday 25 April 2001 | |
| 8H45 | Registration |
| 9H20 | Opening |
| Session 1: Pattern recognition - classification | |
| 9H30 |
A local search method for pattern classification |
| 9H50 | Recognition of consonant-vowel utterances using Support Vector Machines C. Chandra Sekhar, K. Takeda, F. Ikatura, Nagoya Univ. (Japan) |
| 10H10 | Automatic relevance determination for Least Squares Support Vector Machines classifiers T. Van Gestel, J.A.K. Suykens, B. De Moor, J. Vandewalle, K.U. Leuven (Belgium) |
| 10H30 | Coffee break |
| Session 2: Signal processing and vision | |
| 11H00 | Analysis of dynamic perfusion MRI data by neural network A. Wismüller, O. Lange, D.R. Dersch*, K. Hahn, G.L. Leinsinger, Ludwig-Maximilians-Univ. München (Germany), *Crux Cybernetics Corp. (Australia) |
| 11H20 | Visual self-localization with morphological neural networks B. Raducanu, M. Grana, UPV (Spain) |
| 11H40 | A stochastic and competitive network for the separation of sources C.G. Puntonet, A. Mansour*, M.R. Alvarez, B. Prieto, I. Rojas, Univ. Granada (Spain), *RIKEN (Japan) |
| 12H00 | More on stationnary points in Independent Component Analysis V. Vigneron, Univ. Paris I, L. Aubry, CEMIF (France) |
| 12H20 | Lunch |
| Special session 3: Dedicated hardware implementations: perspectives on systems and applications Organised by D. Anguita, M. Valle, Univ. of Genoa (Italy) |
|
| 13H45 | Perspectives on dedicated neural hardware implementations D. Anguita, M. Valle, Univ. of Genoa (Italy) |
| 14H15 | CMOS design of focal plane programmable array processors A. Rodriguez-Vazquez, S. Espejo, R. Dominguez-Castro, R. Carmona, G. Linan, Inst. Microelectronica Sevilla (Spain) |
| 14H35 | Matching analogue hardware with applications using the Products of Experts algorithm P. Fleury, R. Woodburn, A.F. Murray, Univ. Edinburgh (Scotland) |
| 14H55 | A microelectronic implementation of a bioinspired analog matrix for object segmentation of a visual scene J. Cosp, J. Madrenas, Univ. Politec. Catalunya (Spain) |
| 15H15 | Coffee break |
| Special session 4: Novel neural transfer functions Organised by W. Duch, Nicholas Copernicus Univ. (Poland) |
|
| 15H45 | Transfer functions: hidden possibilities for better neural networks W. Duch, N. Jankowski, Nicholas Copernicus Univ. (Poland) |
| 16H05 | Neural networks with orthogonalised transfer functions P. Strumillo, W. Kaminski, Tech. Univ. Lodz (Poland) |
| 16H25 | Optimal transfer function neural networks N. Jankowski, W. Duch, Nicholas Copernicus Univ. (Poland) |
| 16H45 | Constructive density estimation network based on several different separable transfer functions W. Duch, R. Adamczak, Nicholas Copernicus Univ. (Poland), G.H.F. Diercksen, Max-Plack Inst. of Astrophysics (Germany) |
| Poster session: spotlights | |
| Special session 4 | |
| 17H05 | A direct weight address mapping low dimensional cerebellar model neural network (LCMAC) Q. Zhu, T. Gu, J. Xing, Nanjing Normal Univ. (P.R. China) |
| 17H07 | A neural network model for monotone symmetric linear variational inequalities B. He, Nanjing Univ. (P.R. China), L.-Z. Liao, Hong Kong Baptist Univ. (Hong Kong) |
| Special session 3 | |
| 17H09 | Intelligent hardware for identification and control of non-linear systems with SVM A. Boni, F. Bardi, Univ. Trento (Italy) |
| Regular session | |
| 17H11 | Coding the outputs of multilayer feedforward M. Fernandez-Redondo, C. Hernandez-Espinosa, Univ. Jaume I (Spain) |
| 17H13 | Weight initialization methods for multilayer feedforward M. Fernandez-Redondo, C. Hernandez-Espinosa, Univ. Jaume I (Spain) |
| 17H15 | An alternative approach for the evaluation of the neocognitron M. Steuer, P. Caleb-Solly, J. Smith, Univ. West England (UK) |
| 17H17 | Detection of cluster in Self-Organizing Maps for controlling a prostheses using nerve signals M. Bogdan, W. Rosenstiel, Univ. Tübingen (Germany) |
| 17H19 | Poster preview |
| 18H45 | Visit of the "Straffe Hendrik" brewery |
| 19H30 | Conference dinner in the "Straffe Hendrik" brewery |
| Thursday 26 April 2001 | |
| Special session 5: Neural networks and evolutionary/genetic algorithms – hybrid approaches Organised by: Thomas Villmann, Univ. Leipzig (Germany) |
|
| 9H00 | Evolutionary algorithms and neural networks in hybrid systems T. Villmann, Univ. Leipzig (Germany) |
| 9H20 | Lamarckian training of feedforward neural networks P. Cortez, M. Rocha, J. Neves, Univ. Minho (Portugal) |
| 9H40 | Multilayer perceptron learning by genetic algorithms U. Seiffert, Univ. South Australia (Australia) |
| 10H00 | Motor control and movement optimization learned by combining auto-imitative and genetic algorithms K.T. Kalveram, Heinrich-Heine-Univ. (Germany) |
| 10H20 | Designing nearest neighbour classifiers by the evolution of a population of prototypes F. Fernandez, P. Isasi, Univ. Carlos III Madrid (Spain) |
| 10H40 | Investigating the influence of the neighborhood attraction factor to evolution strategies with neighborhood attraction J. Huhse, A. Zell, Univ. Tübingen (Germany) |
| Poster session: spotlights | |
| Special session 5 | |
| 11H00 | A structural genetic algorithm to optimize High Order Neural Network architecture I. Chalkiadakis, G. Rovithakis, M. Zervakis, Tech. Univ. Crete (Greece) |
| 11H02 | Genetic algorithms with crossover based on confidence interval as an alternative to traditional nonlinear regression methods D. Ortiz Boyer, C. Hervas Martinez, Univ. Cordoba, J. Munoz Perez, Univ. Malaga (Spain) |
| 11H04 | The synergy between multideme genetic algorithms and fuzzy systems I. Rojas, J.L. Bernier, E. Ros, F.J. Rojas, C.G. Puntonet, Univ. Granada (Spain) |
| Regular session | |
| 11H06 | Efficient derivative-free Kalman filters for online learning R. van der Merwe, E. A. Wan, Oregon Grad. Inst. (USA) |
| 11H08 | Texture analysis with the Volterra model using conjugate gradient optimisation A.I. Wilmer, Univ. Southampton, T. Stathaki, Imperial Coll. London, S.R. Gunn, R.I. Damper, Univ. Southampton (UK) |
| 11H10 | Weight perturbation learning algorithm with local learning rate adaptation for the classification of remote-sensing images F. Diotalevi, M. Valle, Univ. Genoa (Italy) |
| 11H12 | Coffee break |
| Poster preview | |
| 12H00 | Lunch |
| Special session 6: Neural networks in finance Organised by: M. Cottrell, Univ. Paris I (France) & E. de Bodt, Univ. Lille II (France) - UCL Louvain-la-Neuve (Belgium) |
|
| 13H30 | Some known facts about financial data E. de Bodt, Univ. Lille II (France) & UCL Louvain-la-Neuve (Belgium), M. Cottrell, Univ. Paris I (France) |
| 14H00 | Prediction of financial time series - Application to the BEL20 market index A. Lendasse, J. Lee, E. de Bodt*, V. Wertz, M. Verleysen, UCL Louvain-la-Neuve (Belgium), *Univ. Lille II (France) & UCL Louvain-la-Neuve (Belgium) |
| 14H20 | Prediction of foreign exchange rates by neural network and fuzzy system based techniques V. Kodogiannis, Univ. Westminster, A. Lolis, Univ. Greenwich (UK) |
| 14H40 | Segmentation of switching dynamics with a Hidden Markov Model of neural prediction experts A. Aussem, C. Boutevin, Univ. Blaise Pascal Clermont II (France) |
| 15H00 | Coffee break |
| Session 7: Data processing | |
| 15H30 | Searching the Web: learning based techniques M. Diligenti, M. Gori, M. Maggini and F. Scarselli, Univ. di Siena (Italy) |
| 15H50 | An integrated neural IR system V. J. Hodge, J. Austin, Univ. York (UK) |
| 16H10 | Relevance determination in Learning Vector Quantization T. Bojer, B. Hammer, D. Schunk, K. Tluk von Toschanowitz, Univ. Osnabrück (Germany) |
| 16H30 | Interpretation and comparison of multivariate data partitions E. Alhoniemi, O. Simula, Helsinki Univ. Tech. (Finland) |
| 16H50 | Input pruning for neural gas architectures B. Hammer, Univ. Osnabrück, T. Villmann, Univ. Leipzig (Germany) |
| 18H00 | Half-hour visit of Bruges by boat |
| Friday 27 April 2001 | |
| Session 8: Dynamical systems and chaos | |
| 9H00 | On the short-term-memory of WTA nets B.J. Jain, F. Wysotzki, Tech. Univ. Berlin (Germany) |
| 9H20 | A novel chaotic neural network architecture N. Crook, T. olde Scheper, Oxford Brookes Univ. (UK) |
| 9H40 | Coffee break |
| Special session 9: Artificial neural networks and early vision processing Organised by: D. Charles, C. Fyfe, Univ. of Paisley (Scotland, UK) |
|
| 10H10 | Unsupervised models for processing visual data D. Charles, C. Fyfe, Univ. of Paisley (UK) |
| 10H30 | Canonical correlation analysis in early vision processing M. Borga, H. Knutsson, Linköping Univ. (Sweden) |
| 10H50 | A computational model of monkey grating cells for oriented repetitive alternating patterns T. Lourens, K. Nakadai, H.G. Okuno, H. Kitano, Japan Science & Tech. Corp. (Japan) |
| 11H10 | Extracting motion information with a biologically realistic model retina S.D. Wilke, A. Thiel, C.W. Eurich, M. Greschner*, M. Bongard*, J. Ammermüller*, H. Schwegler, Univ. Bremen, *Carl von Ossietzky Univ. Oldenburg (Germany) |
| 11H30 | Graph extraction from color images T. Lourens, K. Nakadai, H.G. Okuno, H. Kitano, Japan Science & Tech. Corp. (Japan) |
| Poster session: spotlights | |
| Special session 9 | |
| 11H50 | Canonical correlation analysis - A relevance vector approach L. Tan, Chinese Univ. (Hong Kong), C. Fyfe, Univ. Paisley (UK) |
| Regular session | |
| 11H52 | Learning fault-tolerance in Radial Basis Function Networks X. Parra, A. Català, Tech. Univ. Catalonia (Spain) |
| 11H54 | A two steps method: non linear regression and pruning neural network for analyzing multicomponent mixtures C. Hervas Martinez, J.A. Martinez Heras, S. Ventura Soto, M. Silva Rodriguez, Univ. Cordoba (Spain) |
| 11H56 | SOM competition for complex image scene with variant object positions T. El. Tobely, Y. Yoshiki*, R. Tsuda*, N. Tsuruta*, M. Amamiya, Kyushu Univ., *Fukuoka Univ. (Japan) |
| 11H58 | Numerical implementation of continuous Hopfield networks for optimization M. A. Atencia, G. Joya, F. Sandoval, Univ. Malaga (Spain) |
| 12H00 | One-to-many mappings represented on feed-forward networks R. K. Brouwer, Univ. Coll. Cariboo, W. Pedrycz, Univ. Alberta (Canada) |
| 12H02 | Poster preview |
| 12H30 | Lunch |
| Session 10: Neural models and learning | |
| 13H45 | Penalized least squares, model selection, convex hull classes and neural nets G.H.L. Cheang, Nanyang Tech. Univ. (Singapore), A.R. Barron, Yale Univ. (USA) |
| 14H05 | Bayesian decision theory on three layered neural networks Y. Ito, Aichi-Gakuin Univ. (Japan), C. Srinivasan, Univ. Kentucky (USA) |
| 14H25 | Estimation of Hybrid HMM/MLP models J. Rynkiewicz, Univ. Paris I (France) |
| 14H45 | A divide-and-conquer learning architecture for predicting unknown motion P. Wira, J.-P. Urban, J. Gresser, Univ. Mulhouse (France) |
| 15H05 | Rectified Gaussian distributions and the formation of local filters from video data E. Corchado, D. Charles, C. Fyfe, Paisley Univ. (UK) |
| 15H25 | Applications of neuro-fuzzy classification, evaluation and forecasting techniques in agriculture E. Bellei, D. Guidotti*, R. Patacchi*, L. Reyneri, I. Rizzi*, Polit Torino, *Sc. Sup. S. Anna Pisa (Italy) |
| 15H45 | End of conference - Coffee |