Wednesday April 23, 2008
| 08h30 | Registration | ||
| 09h00 | Opening | ||
| 09h10 | Dynamical and recurrent systems, control | ||
| 09h10 | Pruning and Regularisation in Reservoir Computing: a First Insight | ||
| |||
| 09h30 | Design of Oscillatory Recurrent Neural Network Controllers with Gradient based Algorithms | ||
| |||
| 09h50 | Learning Inverse Dynamics: a Comparison | ||
| |||
| 10h10 | Model-Based Reinforcement Learning with Continuous States and Actions | ||
| |||
| 10h30 | Coffee break | ||
| 10h50 | Feature selection, imputation and projection | ||
| 10h50 | Using the Delta Test for Variable Selection | ||
| |||
| 11h10 | Metric adaptation for supervised attribute rating | ||
| |||
| 11h30 | K-nearest neighbours based on mutual information for incomplete data classification | ||
| |||
| 11h50 | Nonlinear data projection on a sphere with controlled trade-off between trustworthiness and continuity | ||
| |||
| 12h10 | Rank-based quality assessment of nonlinear dimensionality reduction | ||
| |||
| 12h30 | Lunch | ||
| 14h00 | Machine learning methods in cancer research Organized by A. Vellido (Polytechnic Univ. Catalonia, Spain), P.J.G.Lisboa (Liverpool John Moores Univ., UK) | ||
| 14h00 | Machine learning in cancer research: implications for personalised medicine | ||
| |||
| 14h20 | Multi-class classification of ovarian tumors | ||
| |||
| 14h40 | A new method of DNA probes selection and its use with multi-objective neural network for predicting the outcome of breast cancer preoperative chemotherapy | ||
| |||
| 15h00 | Feature Selection in Proton Magnetic Resonance Spectroscopy for Brain Tumor Classification | ||
| |||
| 15h20 | A method for robust variable selection with significance assessment | ||
| |||
| 15h40 | Survival SVM: a practical scalable algorithm | ||
| |||
| 16h00 | Machine learning methods in cancer research Poster spotlights | ||
| 16h00 | DSS-oriented exploration of a multi-centre magnetic resonance spectroscopy brain tumour dataset through visualization | ||
| |||
| 16h01 | Handling almost-deterministic relationships in constraint-based Bayesian network discovery : Application to cancer risk factor identification | ||
| |||
| 16h02 | Poster spotlights | ||
| 16h02 | Using graph-theoretic measures to predict the performance of associative memory models | ||
| |||
| 16h03 | A novel autoassociative memory on the complex hypercubic lattice | ||
| |||
| 16h04 | Word recognition and incremental learning based on neural associative memories and hidden Markov models | ||
| |||
| 16h05 | Conditional prediction of time series using spiral recurrent neural network | ||
| |||
| 16h06 | Learning to play Tetris applying reinforcement learning methods | ||
| |||
| 16h07 | QL2, a simple reinforcement learning scheme for two-player zero-sum Markov games | ||
| |||
| 16h08 | Safe exploration for reinforcement learning | ||
| |||
| 16h09 | Similarities and differences between policy gradient methods and evolution strategies | ||
| |||
| 16h10 | Improvement in Game Agent Control Using State-Action Value Scaling | ||
| |||
| 16h11 | Multilayer Perceptrons with Radial Basis Functions as Value Functions in Reinforcement Learning | ||
| |||
| 16h12 | Selection of important input variables for RBF network using partial derivatives | ||
| |||
| 16h13 | A multiple testing procedure for input variable selection in neural networks | ||
| |||
| 16h15 | Computationally Efficient Neural Field Dynamics | ||
| |||
| 16h20 | Coffee break and poster preview | ||
Thursday April 24, 2008
| 09h00 | Biological systems and biologically-inspired networks | ||
| 09h00 | The gamma cycle and its role in the formation of assemblies | ||
| |||
| 09h20 | The impact of axon wiring costs on small neuronal networks | ||
| |||
| 09h40 | An FPGA-based model suitable for evolution and development of spiking neural networks | ||
| |||
| 10h00 | Coffee break | ||
| 10h20 | Clustering and vector quantization | ||
| 10h20 | Self-Organizing Maps for cyclic and unbounded graphs | ||
| |||
| 10h40 | Clustering of Self-Organizing Map | ||
| |||
| 11h00 | Explaining Ant-Based Clustering on the basis of Self-Organizing Maps | ||
| |||
| 11h20 | Phase transitions in Vector Quantization | ||
| |||
| 11h40 | Parallelizing single patch pass clustering | ||
| |||
| 12h00 | Learning Data Representations with Sparse Coding Neural Gas | ||
| |||
| 12h20 | Lunch | ||
| 13h50 | Methodology and standards for data analysis with machine learning tools Organized by D. François (Univ. cat. Louvain, Belgium) | ||
| 13h50 | Methodology and standards for data analysis with machine learning tools | ||
| |||
| 14h10 | A Methodology for Building Regression Models using Extreme Learning Machine: OP-ELM | ||
| |||
| 14h30 | Do we need experts for time series forecasting? | ||
| |||
| 14h50 | Homogeneous bipartition based on multidimensional ranking | ||
| |||
| 15h10 | Feature selection on process fault detection and visualization | ||
| |||
| 15h30 | Classification of chestnuts with feature selection by noise resilient classifiers | ||
| |||
| 15h50 | Methodology and standards for data analysis with machine learning tools Poster spotlights | ||
| 15h50 | GeoKernels: modeling of spatial data on geomanifolds | ||
| |||
| 15h51 | Poster spotlights | ||
| 15h51 | Constructing ensembles of classifiers using linear projections based on misclassified instances | ||
| |||
| 15h52 | A Regularized Learning Method for Neural Networks Based on Sensitivity Analysis | ||
| |||
| 15h53 | A Method for Time Series Prediction using a Combination of Linear Models | ||
| |||
| 15h54 | Interpretable ensembles of local models for safety-related applications | ||
| |||
| 15h55 | Multi-View Forests of Tree-Structured Radial Basis Function Networks Based on Dempster-Shafer Evidence Theory | ||
| |||
| 15h56 | SOM based clustering with instance-level constraints | ||
| |||
| 15h57 | Robust object segmentation by adaptive metrics in Generalized LVQ | ||
| |||
| 15h58 | Magnification Control in Relational Neural Gas | ||
| |||
| 15h59 | Parallel asynchronous neighborhood mechanism for WTM Kohonen network implemented in CMOS technology | ||
| |||
| 16h00 | Initialization mechanism in Kohonen neural network implemented in CMOS technology | ||
| |||
| 16h01 | Neural network hardware architecture for pattern recognition in the HESS2 project | ||
| |||
| 16h02 | Active and reactive use of virtual neural sensors | ||
| |||
| 16h03 | Noise influence on correlated activities in a modular neuronal network: from synapses to functional connectivity | ||
| |||
| 16h04 | Neuromimetic motion indicator for visual perception | ||
| |||
| 16h05 | Coffee break and poster preview | ||
Friday April 25, 2008
| 09h00 | Neural Networks for Computational Neuroscience Organized by D. Meunier, H. Paugam-Moisy (LIRIS-CNRS, France) | ||
| 09h00 | Neural networks for computational neuroscience | ||
| |||
| 09h20 | Emergence of stimulus-specific synchronous response through STDP in recurrent neural networks | ||
| |||
| 09h40 | Visual focus with spiking neurons | ||
| |||
| 10h00 | Simulation of a recurrent neurointerface with sparse electrical connections | ||
| |||
| 10h20 | Neural Networks for Computational Neuroscience Poster spotlights | ||
| 10h20 | Direct and inverse solution for a stimulus adaptation problem using SVR | ||
| |||
| 10h21 | Computational model for amygdala neural networks | ||
| |||
| 10h22 | Coffee break | ||
| 10h45 | Kernel methods | ||
| 10h45 | Factored sequence kernels | ||
| |||
| 11h05 | Regularization path for Ranking SVM | ||
| |||
| 11h25 | An accelerated MDM algorithm for SVM training | ||
| |||
| 11h45 | Approximation of Gaussian process regression models after training | ||
| |||
| 12h05 | Lunch | ||
| 13h45 | Machine Learning Approaches and Pattern Recognition for Spectral Data Organized by T. Villmann (Univ. Leipzig, Germany), E. Merényi (Rice Univ., USA), U. Seiffert (IPK Gatersleben, Germany) | ||
| 13h45 | Machine learning approches and pattern recognition for spectral data | ||
| |||
| 14h05 | Consistency of Derivative Based Functional Classifiers on Sampled Data | ||
| |||
| 14h25 | Generalized matrix learning vector quantizer for the analysis of spectral data | ||
| |||
| 14h45 | Linear Projection based on Noise Variance Estimation - Application to Spectral Data | ||
| |||
| 15h05 | Machine Learning Approaches and Pattern Recognition for Spectral Data Poster spotlights | ||
| 15h05 | Inverting hyperspectral images with Gaussian Regularized Sliced Inverse Regression | ||
| |||
| 15h07 | Poster spotlights | ||
| 15h07 | Comparison of sparse least squares support vector regressors trained in primal and dual | ||
| |||
| 15h08 | On related violating pairs for working set selection in SMO algorithms | ||
| |||
| 15h09 | Discrimination of regulatory DNA by SVM on the basis of over- and under-represented motifs | ||
| |||
| 15h10 | Automatic alignment of medical vs. general terminologies | ||
| |||
| 15h11 | Improving a statistical language model by modulating the effects of context words | ||
| |||
| 15h12 | An emphasized target smoothing procedure to improve MLP classifiers performance | ||
| |||
| 15h13 | A neural model with feedback for robust disambiguation of motion | ||
| |||
| 15h14 | Multilayer perceptron to model the decarburization process in stainless steel production | ||
| |||
| 15h15 | An automatic identifier of Confinement Regimes at JET combining Fuzzy Logic and Classification Trees | ||
| |||
| 15h17 | Combining neural networks and optimization techniques for visuokinesthetic prediction and motor planning | ||
| |||
| 15h18 | Petri nets design based on neural networks | ||
| |||
| 15h19 | Detecting zebra crossings utilizing AdaBoost | ||
| |||
| 15h20 | Coffee break and poster preview | ||