Wednesday 26 April 2006
| 08h30 | Registration | ||
| 09h00 | Opening | ||
| 09h10 | Self-organization, vector quantization and clustering | ||
| 09h10 | Unsupervised clustering of continuous trajectories of kinematic trees with SOM-SD | ||
|
|||
| 09h30 | Magnification control for batch neural gas | ||
|
|||
| 09h50 | Weighted differential topographic function: a refinement of topographic function | ||
|
|||
| 10h10 | Cluster detection algorithm in neural networks | ||
|
|||
| 10h30 | Enhanced maxcut clustering with multivalued neural networks and functional annealing | ||
|
|||
| 10h50 | Coffee break | ||
| 11h10 | Man-Machine-Interfaces - Processing of nervous signals Organized by M. Bogdan, Univ. Tübingen (Germany) |
||
| 11h10 | Artificial neural networks and machine learning for man-machine-interfaces - processing of nervous signals | ||
|
|||
| 11h30 | Linking non-binned spike train kernels to several existing spike train metrics | ||
|
|||
| 11h50 | Spatial filters for the classification of event-related potentials | ||
|
|||
| 12h10 | On-line adaptation of neuro-prostheses with neuronal evaluation signals | ||
|
|||
| 12h30 | Man-Machine-Interfaces - Processing of nervous signals - Poster spotlights | ||
| 12h30 | Using distributed genetic programming to evolve classifiers for a brain computer interface | ||
|
|||
| 12h31 | Lunch | ||
| 13h50 | Vision and applications | ||
| 13h50 | A Cyclostationary Neural Network model for the prediction of the NO2 concentration | ||
|
|||
| 14h10 | Learning Visual Invariance | ||
|
|||
| 14h30 | Change of session break | ||
| 14h40 | Online Learning in Cognitive Robotics Organized by J.J. Steil, Univ. Bielefeld, H. Wersing, Honda Research Institute Europe (Germany) |
||
| 14h40 | Recent trends in online learning for cognitive robots | ||
|
|||
| 15h00 | Extended model of conditioned learning within latent inhibition | ||
|
|||
| 15h20 | construction of a memory management system in an on-line learning mechanism | ||
|
|||
| 15h40 | Adaptive scene-dependent filters in online learning environments | ||
|
|||
| 16h00 | Online Learning in Cognitive Robotics - Poster spotlights | ||
| 16h00 | A multiagent architecture for concurrent reinforcement learning | ||
|
|||
| 16h01 | Some experimental results with a two level memory management system in the multilevel darwinist brain | ||
|
|||
| 16h02 | Poster spotlights | ||
| 16h02 | Robust Local Cluster Neural Networks | ||
|
|||
| 16h03 | Topological Correlation | ||
|
|||
| 16h04 | An algorithm for fast and reliable ESOM learning | ||
|
|||
| 16h05 | EM-algorithm for training of state-space models with application to time series prediction | ||
|
|||
| 16h06 | Time series prediction using DirRec strategy | ||
|
|||
| 16h07 | Consistent estimation of the architecture of multilayer perceptrons | ||
|
|||
| 16h08 | Optimal design of hierarchical wavelet networks for time-series forecasting | ||
|
|||
| 16h09 | Recognition of handwritten digits using sparse codes generated by local feature extraction methods | ||
|
|||
| 16h10 | iterative context compilation for visual object recognition | ||
|
|||
| 16h11 | FPGA implementation of an integrate-and-fire LEGION model for image segmentation | ||
|
|||
| 16h12 | Visual object classification by sparse convolutional neural networks | ||
|
|||
| 16h13 | Modelling switching dynamics using prediction experts operating on distinct wavelet scales | ||
|
|||
| 16h14 | Learning for stochastic dynamic programming | ||
|
|||
| 16h15 | Adaptive Sensor Modelling and Classification using a Continuous Restricted Boltzmann Machine (CRBM) | ||
|
|||
| 16h16 | Non-linear gating network for the large scale classification model CombNET-II | ||
|
|||
| 16h17 | Saliency extraction with a distributed spiking neural network | ||
|
|||
| 16h18 | Connection strategies in neocortical networks | ||
|
|||
| 16h20 | Coffee break and poster preview | ||
| 17h35 | End of day | ||
Thursday 27 April 2006
| 09h00 | Feature extraction and variable projection | ||
| 09h00 | Random Forests Feature Selection with K-PLS: Detecting Ischemia from Magnetocardiograms | ||
|
|||
| 09h20 | Determination of the Mahalanobis matrix using nonparametric noise estimations | ||
|
|||
| 09h40 | Bootstrap feature selection in support vector machines for ventricular fibrillation detection | ||
|
|||
| 10h00 | The permutation test for feature selection by mutual information | ||
|
|||
| 10h20 | Stochastic Processes for Canonical Correlation Analysis | ||
|
|||
| 10h40 | Coffee break | ||
| 11h00 | Visualization methods for data mining F. Rossi, INRIA Rocquencourt (France) |
||
| 11h00 | Visual Data Mining and Machine Learning | ||
|
|||
| 11h30 | Sanger-driven MDSLocalize - a comparative study for genomic data | ||
|
|||
| 11h50 | Visualizing the trustworthiness of a projection | ||
|
|||
| 12h10 | Data topology visualization for the Self-Organizing Map | ||
|
|||
| 12h30 | Visualization methods for data mining - Poster spotlights | ||
| 12h30 | Visual nonlinear discriminant analysis for classifier design | ||
|
|||
| 12h31 | Outlier identification with the Harmonic Topographic Mapping | ||
|
|||
| 12h32 | A new hyperbolic visualization method for displaying the results of a neural gas model: application to Webometrics | ||
|
|||
| 12h33 | Lunch | ||
| 14h00 | Semi-blind approaches for Source Separation and Independent Component Analysis (ICA) I Organized by M. Babaie-Zadeh, Sharif Univ. Tech. (Iran), C. Jutten, CNRS – Univ. J. Fourier – INPG (France) |
||
| 14h00 | Semi-Blind Approaches for Source Separation and Independent component Analysis | ||
|
|||
| 14h20 | Bayesian source separation: beyond PCA and ICA | ||
|
|||
| 14h40 | A survey of Sparse Component Analysis for blind source separation: principles, perspectives, and new challenges | ||
|
|||
| 15h00 | Change of session break | ||
| 15h10 | Semi-blind approaches for Source Separation and Independent Component Analysis (ICA) II | ||
| 15h10 | Source separation with priors on the power spectrum of the sources | ||
|
|||
| 15h30 | A time-scale correlation-based blind separation method applicable to correlated sources | ||
|
|||
| 15h50 | Independent dynamics subspace analysis | ||
|
|||
| 16h10 | Non-orthogonal Support Width ICA | ||
|
|||
| 16h30 | Hierarchical markovian models for joint classification, segmentation and data reduction of hyperspectral images | ||
|
|||
| 16h50 | Semi-blind approaches for Source Separation and Independent Component Analysis (ICA) - Poster spotlights | ||
| 16h50 | A simple idea to separate convolutive mixtures in an undetermined scenario | ||
|
|||
| 16h51 | FastISA: A fast fixed-point algorithm for independent subspace analysis | ||
|
|||
| 16h52 | Discriminacy of the minimum range approach to blind separation of bounded sources | ||
|
|||
| 16h54 | Poster spotlights | ||
| 16h53 | Entropy-based principle and generalized contingency tables | ||
|
|||
| 16h54 | On the selection of hidden neurons with heuristic search strategies for approximation | ||
|
|||
| 16h55 | Lag selection for regression models using high-dimensional mutual information | ||
|
|||
| 16h56 | Learning what is important: feature selection and rule extraction in a virtual course | ||
|
|||
| 16h57 | Data mining techniques for feature selection in blood cell recognition | ||
|
|||
| 16h58 | A Gaussian process latent variable model formulation of canonical correlation analysis | ||
|
|||
| 16h59 | Designing neural network committees by combining boosting ensembles | ||
|
|||
| 17h00 | Using Regression Error Characteristic Curves for Model Selection in Ensembles of Neural Networks | ||
|
|||
| 17h01 | Diversity creation in local search for the evolution of neural network ensembles | ||
|
|||
| 17h02 | Immune Network based Ensembles | ||
|
|||
| 17h03 | Classification by means of Evolutionary Response Surfaces | ||
|
|||
| 17h04 | Hierarchical analysis of GSM network performance data | ||
|
|||
| 17h05 | Learning with monotonicity requirements for optimal routing with end-to-end quality of service constraints | ||
|
|||
| 17h10 | Coffee break and poster preview | ||
| 18h25 | End of day | ||
Friday 28 April 2006
| 09h00 | Biologically inspired models | ||
| 09h00 | Evolving multi-segment 'super-lamprey' CPG's for increased swimming control | ||
|
|||
| 09h20 | Exploring the role of intrinsic plasticity for the learning of sensory representations | ||
|
|||
| 09h40 | Kernel methods | ||
| 09h40 | LS-SVM functional network for time series prediction | ||
|
|||
| 10h00 | Synthesis of maximum margin and multiview learning using unlabeled data | ||
|
|||
| 10h20 | Efficient Forward Regression with Marginal Likelihood | ||
|
|||
| 10h40 | Coffee break | ||
| 11h00 | Nonlinear dynamics Organized by N. Crook, T. olde Scheper, Oxford Brookes University (UK) |
||
| 11h00 | Nonlinear dynamics in neural computation | ||
|
|||
| 11h30 | Dynamical reservoir properties as network effects | ||
|
|||
| 11h50 | Nonlinear transient computation and variable noise tolerance | ||
|
|||
| 12h10 | Cultures of dissociated neurons display a variety of avalanche behaviours | ||
|
|||
| 12h30 | Lunch | ||
| 13h45 | Neural Networks and Machine Learning in Bioinformatics - Theory and Applications Organized by B. Hammer, Clausthal Univ. Tech. (Germany), S. Kaski, Helsinki Univ. Tech. (Finland), U. Seiffert, IPK Gatersleben (Germany), T. Villmann, Univ. Leipzig (Germ |
||
| 13h45 | Neural networks and machine learning in bioinformatics - theory and applications | ||
|
|||
| 14h15 | Using sampling methods to improve binding site predictions | ||
|
|||
| 14h35 | Margin based Active Learning for LVQ Networks | ||
|
|||
| 14h55 | Classification of Boar Sperm Head Images using Learning Vector Quantization | ||
|
|||
| 15h15 | Neural Networks and Machine Learning in Bioinformatics - Theory and Applications - Poster spotlights | ||
| 15h15 | Selection of more than one gene at a time for cancer prediction from gene expression data | ||
|
|||
| 15h16 | Visualizing gene interaction graphs with local multidimensional scaling | ||
|
|||
| 15h17 | Fuzzy image segmentation with Fuzzy Labelled Neural Gas | ||
|
|||
| 15h18 | Elucidating the structure of genetic regulatory networks: a study of a second order dynamical model on artificial data | ||
|
|||
| 15h19 | Poster spotlights | ||
| 15h19 | OnlineDoubleMaxMinOver: a simple approximate time and information efficient online Support Vector Classification method | ||
|
|||
| 15h20 | Variants of Unsupervised Kernel Regression: General cost functions | ||
|
|||
| 15h21 | Degeneracy in model selection for SVMs with radial Gaussian kernel | ||
|
|||
| 15h22 | Evolino for recurrent support vector machines | ||
|
|||
| 15h23 | Hybrid generative/discriminative training of radial basis function networks | ||
|
|||
| 15h24 | Rotation-based ensembles of RBF networks | ||
|
|||
| 15h25 | Learning and discrimination through STDP in a top-down modulated associative memory | ||
|
|||
| 15h26 | Gaussian and exponential architectures in small-world associative memories | ||
|
|||
| 15h27 | Parallel hardware implementation of a broad class of spiking neurons using serial arithmetic | ||
|
|||
| 15h28 | Generalization properties of spiking neurons trained with ReSuMe method | ||
|
|||
| 15h29 | A sequence-encoding neural network for face recognition | ||
|
|||
| 15h30 | Freeform surface induction from projected planar curves via neural networks | ||
|
|||
| 15h31 | The combination of STDP and intrinsic plasticity yields complex dynamics in recurrent spiking networks | ||
|
|||
| 15h32 | Reducing policy degradation in neuro-dynamic programming | ||
|
|||
| 15h34 | Probabilistic classifiers and time-scale representations: application to the monitoring of a tramway guiding system | ||
|
|||
| 15h35 | Pattern analysis in illicit heroin seizures: a novel application of machine learning algorithms | ||
|
|||
| 15h40 | Coffee break and poster preview | ||
| 17h00 | End of conference | ||