Wednesday 27 April 2005 | |
8h30 | Registration |
9h00 | Opening |
Session1: Clustering, quantization, and self-organization | |
09h10 | Architecture of emergent self-organizing maps to reduce projection errors |
A. Ultsch, L. Herrman, Univ. Marburg (Germany) | |
09h30 | A new learning algorithm for incremental self-organizing maps |
Y. Prudent, A. Ennaji, PSI Lab. (France | |
09h50 | The dynamics of Learning Vector Quantization |
M. Biehl, A. Ghosh, Univ. Groningen (The Netherlands), B. Hammer, Clausthal Univ. Tech. (Germany) | |
10h10 | TreeGNG - hierarchical topological clustering |
K. Doherty, R. Adams, N. Davey, Univ. Hertfordshire (U.K.) | |
10h30 | Coffee break |
Special
session 2: Dynamical and Numerical Aspects of Neural Computing |
|
10h50 | Two or three things that we (intend to) know about Hopfield and Tank networks |
M. Atencia, G. Joya, F. Sandoval, Univ. Málaga (Spain) | |
11h10 | The Nonlinear Dynamic State neuron |
N. Crook, W. J. Goh, M. Hawarat, Oxford Brookes Univ. (U.K.) | |
11h30 | Stability of backpropagation-decorrelation efficient O(N) recurrent learning |
J. J. Steil, Bielefeld Univ. (Germany) | |
12h10 | Stochastic analysis of the Abe formulation of Hopfield networks |
M.
Kratz, Univ. René Descartes, Paris V (France), M. Atencia, G. Joya,
Univ. Málaga (Spain) Poster spotlights |
|
Poster spotlights | |
12h30 | Using generic neural networks in the control and prediction of grasp postures |
F. Carenzi, P. Gorce, LESP, Y. Burnod, M. Maier, Inserm (France) | |
12h31 | Exponential stability of stochastic cellular neural networks |
M. Joy, Kingston Univ. (U.K.) | |
12h35 | Lunch |
Session 3: Learning | |
14h00 | Organization properties of open networks of cooperative neuro-agents |
J.P. Manu, P. Glize, Univ. Paul Sabatier (France) | |
14h20 | A ridgelet kernel regression model using genetic algorithm |
S. Yang, M. Wang, L. Jiao, Xidian Univ. (China) | |
14h40 | Boosting by weighting boundary and erroneous samples |
V. Gómez-Verdejo, M. Ortega-Moral, J. Arenas-García, A. R. Figueiras-Vidal, Univ. Carlos III de Madrid (Spain) | |
Special
session 4: Artificial Neural Networks and Prognosis in Medicine Organized by J.M. Jerez, Univ. Malaga, Spain, L. Franco, Univ. Oxford, U.K. |
|
15h00 | Artificial neural networks and prognosis in medicine. Survival analysis in breast cancer patients |
J. Jerez, Univ. Málaga (Spain), L. Franco, Oxford Univ. (U.K.), E. Alba, Hosp. Univ. Málaga (Spain) | |
15h20 | An artificial neural network for analysing the survival of patients with colorectal cancer |
R. Bittern*, A. Cuschieri*, S. Dolgobrodov, R. Marshall, P. Moore, Univ. Manchester (England), R. Steele, *Univ.Dundee (Scotland) | |
15h40 | Artificial intelligence techniques for the prediction of bladder cancer progression |
M. Abbod, J. W.F. Catto, M. Chen, D. A. Linkens, F. C. Hamdy, Univ. Sheffield (U.K.) | |
16h00 | Artificial neural network modeling to predict extent of tumor in men with prostate cancer |
E. Gamito, C. O'Donnell*, T. Ashutosh, Cornell Univ. (USA), D. Crawford, *Univ. Colorado (USA) | |
16h20 | Computational models of ICSI prognosis |
H. Liu, A. Kshirsagar*, J. Ku, D. Lamb, Baylor Coll. Medicine (USA), C. Niederberger, *Univ. Illinois Chicago (USA) | |
16h40 | Handling outliers and missing data in brain tumour clinical assessment using t-GTM |
A. Vellido*, P. J.G. Lisboa, Liverpool John Moores Univ. (England), D. Vicente, *Polytec. Univ. Catalonia (Spain) | |
Poster spotlights | |
17h00 | Predicting bed demand in a hospital using neural networks and arima models: a hybrid approach |
M. Joy, S. Jones, Kingston Univ. (U.K.) | |
17h01 | Functional topographic mapping for robust handling of outliers in brain tumour data |
A. Vellido, Polytec. Univ. Catalonia (Spain), P. J.G. Lisboa, Liverpool John Moores Univ. (England) | |
17h02 | Relevance learning for mental disease classification |
B. Hammer, Clausthal Univ. Tech. (Germany), A. Rechtien, Univ. Osnabrueck (Germany), M. Strickert, IPK (Germany), T. Villmann, Univ. Leipzig (Germany) | |
17h03 | Automatic classification of prostate cancer using pseudo-gaussian radial basis function neural network |
O. Valenzuela, I. Rojas, F. Rojas, L. Marquez, Univ. Granada (Spain) | |
Session 5: Posters I | |
17h04 | Artificial neural network fusion: Application to Arabic words recognition |
N. Farah, M. T. Khadir, Univ. Badji Mokhtar Annaba (Algeria) | |
17h05 | Adaptive Simultaneous Perturbation Based Pruning Algorithm for Neural Control Systems |
J. Ni, O. Song, Nanyang Tech. Univ. (Singapore) | |
17h06 | Modified backward feature selection by cross validation |
S. Abe, Kobe Univ. (Japan) | |
17h07 | Initialisation improvement in engineering feedforward ANN models |
A. Krimpenis, G.-C. Vosniakos, Nat. Tech. Univ. Athens (Greece) | |
17h08 | An On-line Fisher Discriminant |
M. Ortega-Moral, V. Gómez-Verdejo, J. Arenas-García, A. R. Figueiras-Vidal, Univ. Carlos III de Madrid (Spain) | |
17h09 | Averaging on Riemannian manifolds and unsupervised learning using neural associative memory |
D. Nowicki, O. Dekhtyarenko, Nat. Acad. Sci. (Ukraine) | |
17h10 | A Stability Condition for Neural Network Control of Uncertain Systems |
P. Clawom, Rajamangala Inst. Tech., S. Kuntanapreeda, King Mongkuts Inst. Tech. North Banghkok (Thailand) | |
17h11 | A new approach based on wavelet-ica algorithms for fetal electrocardiogram extraction |
B. Azzerboni, F. La Foresta*, Univ. Messina, , N. Mammone, F. C. Morabito, *Univ. Mediterranea of Reggio Calabria (Italy) | |
17h12 | Graph-based normalization |
C. Aaron, Univ. Paris 1 (France) | |
17h13 | Domain expert approximation through oracle learning |
J. Menke, T. Martinez, Brigham Young Univ. (USA) | |
17h14 | Generalised Cross Validation for Noise-Free Data |
T. Dodd, T. Ladoni, Univ. Sheffield (U.K.) | |
17h15 | Coffee break and poster preview |
Thursday 28 April 2005 | |
Session 6: Perceptrons and Multi-Layer Perceptrons | |
09h00 | Neural network classification using Shannon's entropy |
L. Silva, J. M. Sá, Univ. Porto (Portugal), L. Alexandre, IT Covilhã (Portugal) | |
09h20 | Efficient estimation of multidimensional regression model with multilayer perceptron |
J. Rynkiewicz, Univ. Paris I (France) | |
09h40 | Performance of EMI based mine detection using back-propagation neural networks |
M. Draper, T. Kocak, Univ. Central Florida (USA) | |
10h00 | Perceptron Learning with Discrete Weights |
J. M. Sá, C. Felgueiras, Univ. Porto (Portugal) | |
10h20 | Coffee break |
Special
session 7: Evolutionary and neural computation Organized by C. Igel, Ruhr-Univ. Bochum, B. Sendhoff, Honda Research Inst. Europe (Germany) |
|
10h50 | Synergies between Evolutionary and Neural Computation |
C. Igel, Ruhr-Univ. Bochum, B. Sendhoff, Honda Research Inst. Europe (Germany) | |
11h10 | Evolutionary framework for the construction of diverse hybrid ensembles |
A. Chandra, X. Yao, Univ. Birmingham (U.K.) | |
11h30 | Efficient reinforcement learning through Evolutionary Acquisition of Neural Topologies |
Y. Kassahun, G. Sommer, Christian Albrechts Univ. (Germany) | |
11h50 | Evolving neural networks: Is it really worth the effort? |
J. Bullinaria, Univ. Birmingham (U.K.) | |
Poster spotlights | |
12h10 | Efficient evolutionary optimization using individual-based evolution control and neural networks: A comparative study |
L. Graening, Tech. Univ. Ilmenau, Y. Jin, B. Sendhoff, Honda Res. Inst. Europe (Germany) | |
12h11 | Applications of multi-objective structure optimization |
A. Gepperth, S. Roth, Ruhr-Univ. Bochum (Germany) | |
12h15 | Lunch |
Session 8: Independent Component Analysis | |
13h45 | Empirical evidence of the linear nature of magnetoencephalograms |
A. Honkela, T. Östman, R. Vigário, Helsinki Univ. Tech. (Finland) | |
14h05 | To apply score function difference based ICA algorithms to high-dimensional data |
K. Zhang, L.-W. Chan, Chinese Univ. Hong Kong (China) | |
14h25 | Generative Independent Component Analysis for EEG classification |
S. Chiappa, D. Barber, IDIAP Res. Inst. (Switzerland) | |
Special
session 9: Classification using non-standard metrics Organized by B. Hammer, Clausthal Univ. Tech., T. Villmann, Univ. Leipzig (Germany) |
|
14h45 | Classification using non-standard metrics |
B. Hammer, Clausthal Univ. Tech., T. Villmann, Univ. Leipzig (Germany) | |
15h15 | Clustering using a random walk based distance measure |
L. Yen, D. Vanvyve, F. Wouters, F. Fouss, M. Verleysen, M. Saerens, Univ. cat. Louvain (Belgium) | |
15h35 | A probabilistic framework for mismatch and profile string kernels |
A. Vinokourov*, A. Soklakov, Royal Holloway, Univ. London, C. Saunders, *Univ. Southampton (U.K.) | |
15h55 | Generalized Relevance LVQ with Correlation Measures for Biological Data |
M. Strickert, N. Sreenivasulu, W. Weschke, U. Seiffert, IPK-Gatersleben T. Villmann, Univ. Leipzig (Germany) | |
Poster spotlights | |
16h15 | Non-Euclidean metrics for similarity search in noisy datasets |
D. Francois, V. Wertz, M. Verleysen, Univ. cat. Louvain (Belgium) | |
16h16 | Fuzzy ROC Curves for the One Class SVM: Application to Intrusion Detection |
P. Evangelista, P. Bonissone, M. Embrechts, B. Szymanski, Rensselaer Polyt. Inst. (USA) | |
16h17 | Fuzzy Proximal Support Vector Classification via Generalized Eigenvalues |
J. Jayadeva, R. Khemchandani, S. Chandra, Indian Inst. Tech. Delhi (India) | |
16h18 | Usage Guided Clustering of Web Pages with the Median Self Organizing Map |
F. Rossi, A. El Golli, Y. Lechevallier, INRIA Rocquencourt (France) | |
16h19 | Mixed Topological Map |
M. Lebbah*, A. Chazottes*, F. Badran, CNAM (France), S. Thiria, *Univ. Paris 6 France) | |
16h20 | Linear algebra for time series of spikes |
A. Carnell, R. Daniel, University of Bath (U.K.) | |
Session 10: Posters II | |
16h21 | Relevance determination in reinforcement learning |
K. Tluk v. Toschanowitz*, B. Hammer, Clausthal Univ. Tech., H. Ritter, *Univ. Bielefeld (Germany) | |
16h22 | Feature selection for high-dimensional industrial data |
M. Bensch, M. Schröder, M. Bogdan, W. Rosenstiel, Eberhard-Karls-Univ. Tübingen (Germany) | |
16h23 | Adaptive robot learning in a non-stationary environment |
K. Främling, Helsinki Univ. Tech. (Finland) | |
16h24 | Phase transition in sparse associative neural networks |
O. Dekhtyarenko, Nat. Acad. Sci. (Ukraine), T. Valery, C. Fyfe, Univ. Paisley (Scotland) | |
16h25 | Neuromimetic model of interval timing |
C. Touzet, P. Demoulin, Univ. Provence, B. Burle*, F. Vidal, IMNSSA, F. Macar, *Lab. Neurobiologie Cognition (France) | |
16h26 | Contextual Processing of Graphs using Self-Organizing Maps |
M. Hagenbuchner, Univ. Wollongong (Australia), A. Sperduti, Univ. Padova (Italy), A. C. Tsoi, Australian Res. Council (Australia) | |
16h27 | Structural feature selection for wrapper methods |
G. Bontempi, Univ. Libre Bruxelles (Belgium) | |
16h28 | Coverage-performance estimation for classification with ambiguous data |
T. Trappenberg, Dalhousie Univ. (Canada) | |
16h29 | UWB radar target identification based on linear RBFNN |
M. Wang, S. Yang, Xidian Univ. (China) | |
16h20 | Coffee break and poster preview |
Friday 29 April 2005 | |
Session 11: Biologically inspired models | |
09h00 | A multi-modular associator network for simple temporal sequence learning and generation |
L. Michael, T. Trappenberg, A. Fine, Dalhousie Univ. (Canada) | |
09h20 | Attractor neural networks with patchy connectivity |
C. Johansson, M. Rehn, A. Lansner, Royal Inst. Tech. (Sweden) | |
09h40 | Isolated word recognition using a Liquid State Machine |
D. Verstraeten, B. Schrauwen, Ghent Univ. (Belgium) | |
10h00 | New evidences for sparse coding strategy employed in visual neurons: from the image processing and nonlinear approximation viewpoint |
S. Tan, L. Jiao, Inst. Intelligent Information Proc. (China) | |
10h20 | Coffee break |
Special
session 12: Kernel methods and the exponential family Organized by A. Smola, National ICT (Australia), S. Canu, INSA Rouen (France) |
|
10h40 | The exponential family and Kernels for learning |
A. Smola, National ICT (Australia), S. Canu, INSA Rouen (France) | |
11h10 | Joint Regularization |
K. M. Borgwardt, Ludwig-Maximilians-Univ. (Germany), O. Guttman, S.V.N. Vishwanathan, A. Smola, National ICT (Australia) | |
11h30 | A Class of Kernels For Sets of Vectors |
F. Desobry*, M. Davy, CNRS - LAGIS (France), W. Fitzgerald, *Univ. Cambridge (U.K.) | |
11h50 | Support Vector Machine For Functional Data Classification |
N. Villa, Univ. Toulouse Le Mirail, F. Rossi, INRIA Rocquencourt (France) | |
12h10 | Translation invariant classification of non-stationary signals |
V. Guigue, A. Rakotomamonjy, S. Canu, PSI laboratory (France) | |
12h30 | Lunch |
Session 13: Applications | |
14h00 | Chemical similarity searching using a neural graph matcher |
S. Klinger, J. Austin, Univ. York (U.K.) | |
14h20 | SVM and pattern-enriched common fate graphs for the game of go |
L. Ralaivola, L. Wu, P. Baldi, Inst. Genomics Bioinformatics (USA) | |
14h40 | Using CMU PIE Human Face Database to a Convolutional Neural Network - Neocognitron |
J. H. Saito*, T. V. de Carvalho*, M. Hirakuri*, A. Saunite*, A. N. Ide, Univ. Genoa (Italy), S. Abib, *Federal Univ. São Carlos (Brazil) | |
15h00 | Morphological memories for feature extraction in hyperspectral images |
M. Graña, A. d'Anjou, X. Albizuri, Univ. Pais Vasco (Spain) | |
Session 14: Posters III | |
15h20 | Mutual information and gamma test for input selection |
N. Reyhani, J. Hao, Y. Ji, A. Lendasse, Helsinki Univ. Tech. (Finland) | |
15h21 | Pruned lazy learning models for time series prediction |
A. Sorjamaa, A. Lendasse, Helsinki Univ. Tech. (Finland), M. Verleysen, Univ. cat. Louvain (Belgium) | |
15h22 | A new wrapper method for feature subset selection |
N. Sánchez-Maroño, A. Alonso-Betanzos, Univ. A Coruña, E. Castillo, Univ. Cantabria (Spain) | |
15h23 | Analysis of contrast functions in a genetic algorithm for post-nonlinear blind source separation |
F. Rojas, C. García Puntonet, I. Rojas, Univ. Granada (Spain) | |
15h24 | Sparse Bayesian promoter based gene classification |
K. Khoon Lee, G. Cawley, Univ. East Anglia, M. Bevan, John Innes Inst. (U.K.) | |
15h25 | Graph projection techniques for Self-Organizing Maps |
G. Pölzlbauer, A. Rauber, Vienna Univ. Tech., M. Dittenbach, E-Commerce Competence Center (Austria) | |
15h26 | A Neural Network that helps building a Nonlinear Dynamical model of a Power Amplifier |
G. Stegmayer, Politec. Torino (Italy), O. Chiotti, Univ. Tec. Nacion. (Argentina), G. Orengo, Univ. Roma II (Italy) | |
15h27 | Contextual priming for artificial visual perception |
H. Guillaume, N. Denquive, P. Tarroux, LIMSI-CNRS (France) | |
15h28 | Learning to classify a collection of images and texts |
P. Saragiotis, B. Vrusias, K. Ahmad, University of Surrey (U.K.) | |
15h29 | SOM computing on Graphic Process Unit |
Z. Luo, L. Hongzhi, Z. Yang, X. Wu, China Univ. Geoscience Wuhan (P.R.China) | |
15h30 | Novel Algorithm for Eliminating the Boundary Effect in Standard SOM |
K. Marzouki, T. Yamakawa, Kyushu Inst. Tech. (Japan) | |
15h31 | Adaline-based estimation of power harmonics |
D. Ould Abdeslam, J. Mercklé, P. Wira, Univ. Mulhouse (France) | |
15h32 | Rader target recognition using SVMs with a wrapper feature selection driven by immune clonal algorithm |
X. Zhang, S. Wang, S. Tan, L. Jiao, Inst. Intelligent Information Proc. (China) | |
15h33 | Experimental validation of a synapse model by adding synaptic conductances to excitable endocrine cells in culture |
S. Boussa, M. Marin, F. LeFoll, A. Faure, F. Leboulanger, Univ. Havre (France) | |
15h34 | Ultra-wideband Nearfield Adaptive Beamforming based on a RBF Neural Network |
M. Wang, S. Yang, Xidian Univ. (China) | |
15h35 | Support vector algorithms as regularization networks |
A. Caponnetto, L. Rosasco, F. Odone, A. Verri, Univ. Genova (Italy) | |
15h36 | STDP in 'small world' networks |
K. Kube, A. Herzog, B. Michaelis, A. de Lima, T. Voigt, Otto-von-Guericke-Univ. Magdeburg (Germany) |
|
15h40 | Coffee break and poster preview |
17h00 | End of conference |