Wednesday April 24, 2013
Thursday April 25, 2013
Friday April 26, 2013
| 08h30 | Registration | ||
| 09h00 | Opening | ||
| 09h10 | Machine Learning Methods for Processing and Analysis of Hyperspectral Data Organized by Andreas Backhaus, Marika Kästner, Udo Seiffert, Thomas Villmann (Germany) | ||
| 09h10 | Processing Hyperspectral Data in Machine Learning | ||
| |||
| 09h30 | Multi-view feature extraction for hyperspectral image classification | ||
| |||
| 09h50 | Regularization in relevance learning vector quantization using l1-norms | ||
| |||
| 10h10 | Recurrent networks and modeling | ||
| 10h10 | Mixed order associative networks for function approximation, optimisation and sampling | ||
| |||
| 10h30 | Auto-encoder pre-training of segmented-memory recurrent neural networks | ||
| |||
| 10h50 | Recurrent networks and modeling Poster spotlights | ||
| 10h50 | Error entropy criterion in echo state network training | ||
| |||
| 10h51 | Perceptual grouping through competition in coupled oscillator networks | ||
| |||
| 10h52 | Using Wikipedia with associative networks for document classification | ||
| |||
| 10h53 | Automated operational states detection for drilling systems control in critical conditions | ||
| |||
| 10h54 | Analysis of Synaptic Weight Distribution in an Izhikevich Network | ||
| |||
| 10h55 | Percolation model of axon guidance | ||
| |||
| 10h56 | Efficient VLSI Architecture for Spike Sorting Based on Generalized Hebbian Algorithm | ||
| |||
| 10h57 | Coffee break | ||
| 11h20 | Dimensionality reduction | ||
| 11h20 | Soft rank neighbor embeddings | ||
| |||
| 11h40 | Multiple Kernel Self-Organizing Maps | ||
| |||
| 12h00 | Semi-Supervised Vector Quantization for proximity data | ||
| |||
| 12h20 | Dimensionality reduction Poster spotlights | ||
| 12h20 | Sensitivity to parameter and data variations in dimensionality reduction techniques | ||
| |||
| 12h21 | Lunch | ||
| 13h50 | Image, signal and time series analysis | ||
| 13h50 | A nuclear-norm based convex formulation for informed source separation | ||
| |||
| 14h10 | Frequency-Dependent Peak-Over-Threshold algorithm for fault detection in the spectral domain | ||
| |||
| 14h30 | Activity Date Estimation in Timestamped Interaction Networks | ||
| |||
| 14h50 | Novelty detection in image recognition using IRF Neural Networks properties | ||
| |||
| 15h10 | Image, signal and time series analysis Poster spotlights | ||
| 15h10 | Non-Euclidean independent component analysis and Oja's learning | ||
| |||
| 15h11 | Automatic Singular Spectrum Analysis for Time-Series Decomposition | ||
| |||
| 15h12 | Dimension reduction for individual ica to decompose FMRI during real-world experiences: principal component analysis vs. canonical correlation analysis | ||
| |||
| 15h13 | Machine Learning Techniques for Short-Term Electric Power Demand Prediction | ||
| |||
| 15h14 | Unsupervised non-linear neural networks capture aspects of floral choice behaviour | ||
| |||
| 15h15 | Feature selection | ||
| 15h15 | GA-KDE-Bayes: an evolutionary wrapper method based on non-parametric density estimation applied to bioinformatics problems | ||
| |||
| 15h35 | Risk Estimation and Feature Selection | ||
| |||
| 15h55 | Random Brains: An ensemble method for feature selection with neural networks | ||
| |||
| 16h15 | Feature selection Poster spotlights | ||
| 16h15 | A distributed wrapper approach for feature selection | ||
| |||
| 16h16 | Feature Selection for Footwear Shape Estimation | ||
| |||
| 16h17 | Efficient prediction of x-axis intercepts of discrete impedance spectra | ||
| |||
| 16h18 | Evolutionary computation based system decomposition with neural networks | ||
| |||
| 16h19 | Coffee break and poster preview | ||
Thursday April 25, 2013
| 09h00 | Reinforcement learning, control and optimization | ||
| 09h00 | Fast online adaptivity with policy gradient: example of the BCI ``P300''-speller | ||
| |||
| 09h20 | Locally Weighted Least Squares Temporal Difference Learning | ||
| |||
| 09h40 | Learning control under uncertainty: A probabilistic Value-Iteration approach | ||
| |||
| 10h00 | Reinforcement learning, control and optimization Poster spotlights | ||
| 10h00 | Ensembles for Continuous Actions in Reinforcement Learning | ||
| |||
| 10h01 | An empirical analysis of reinforcement learning using design of experiments | ||
| |||
| 10h02 | Hierarchical Reinforcement Learning for Robot Navigation | ||
| |||
| 10h03 | Least-squares temporal difference learning based on extreme learning machine | ||
| |||
| 10h04 | Binary particle swarm optimisation with improved scaling behaviour | ||
| |||
| 10h05 | Dynamic Placement with Connectivity for RSNs based on a Primal-Dual Neural Network | ||
| |||
| 10h06 | Machine Learning for multimedia applications Organized by David Picard, Philippe-Henri Gosselin(France) | ||
| 10h06 | Machine Learning and Content-Based Multimedia Retrieval | ||
| |||
| 10h26 | Machine Learning for multimedia applications Poster spotlights | ||
| 10h26 | Learning associative spatiotemporal features with non-negative sparse coding | ||
| |||
| 10h27 | Content-based image retrieval with hierarchical Gaussian Process bandits with self-organizing maps | ||
| |||
| 10h28 | Coffee break | ||
| 10h50 | Clustering | ||
| 10h50 | Clustering the Vélib’ origin-destinations flows by means of Poisson mixture models | ||
| |||
| 11h10 | Delaunay simplices pruning based clustering | ||
| |||
| 11h30 | Hierarchical and multiscale Mean Shift segmentation of population grids | ||
| |||
| 11h50 | Bayesian non parametric inference of discrete valued networks | ||
| |||
| 12h10 | ONP-MF: An Orthogonal Nonnegative Matrix Factorization Algorithm with Application to Clustering | ||
| |||
| 12h30 | Linear spectral hashing | ||
| |||
| 12h50 | Clustering Poster spotlights | ||
| 12h50 | Normalized cuts clustering with prior knowledge and a pre-clustering stage | ||
| |||
| 12h51 | Network community detection with edge classifiers trained on LFR graphs | ||
| |||
| 12h52 | Lunch | ||
| 14h20 | Regression and forecasting | ||
| 14h20 | Decoding stimulation intensity from evoked ECoG activity using support vector regression | ||
| |||
| 14h40 | Neurally imprinted stable vector fields | ||
| |||
| 15h00 | Ensembles of genetically trained artificial neural networks for survival analysis | ||
| |||
| 15h20 | Regression and forecasting Poster spotlights | ||
| 15h20 | Optimization of Gaussian process hyperparameters using Rprop | ||
| |||
| 15h21 | Are Rosenblatt multilayer perceptrons more powerfull than sigmoidal multilayer perceptrons? From a counter example to a general result | ||
| |||
| 15h22 | Detection and quantification in real-time polymerase chain reaction | ||
| |||
| 15h23 | Temperature Forecast in Buildings Using Machine Learning Techniques | ||
| |||
| 15h24 | Forecasting Financial Markets with Classified Tactical Signals | ||
| |||
| 15h25 | Developments in kernel design Organized by Lluís A. Belanche (Spain) | ||
| 15h25 | Developments in kernel design | ||
| |||
| 15h45 | A quotient basis kernel for the prediction of mortality in severe sepsis patients | ||
| |||
| 16h05 | Synthetic over-sampling in the empirical feature space | ||
| |||
| 16h25 | Developments in kernel design Poster spotlights | ||
| 16h25 | Multi-scale Support Vector Machine Optimization by Kernel Target-Alignment | ||
| |||
| 16h26 | Handling missing values in kernel methods with application to microbiology data | ||
| |||
| 16h27 | Coffee break and poster preview | ||
Friday April 26, 2013
| 09h00 | Human Activity and Motion Disorder Recognition: towards smarter Interactive Cognitive Environments Organized by Jorge Luis Reyes-Ortiz, Alessandro Ghio, Xavier Parra-Llanas, Davide Anguita, Joan Cabestany, Andreu Català(Spain) | ||
| 09h00 | Human Activity and Motion Disorder Recognition: towards smarter Interactive Cognitive Environments | ||
| |||
| 09h20 | A heterogeneous database for movement knowledge extraction in Parkinson’s disease | ||
| |||
| 09h40 | Long term analysis of daily activities in smart home | ||
| |||
| 10h00 | Human Activity and Motion Disorder Recognition: towards smarter Interactive Cognitive Environments Poster spotlights | ||
| 10h00 | Sensor Positioning for Activity Recognition Using Multiple Accelerometer-Based Sensors | ||
| |||
| 10h01 | Multi-user Blood Alcohol Content estimation in a realistic simulator using Artificial Neural Networks and Support Vector Machines | ||
| |||
| 10h02 | Human activity recognition competition | ||
| 10h02 | A Public Domain Dataset for Human Activity Recognition using Smartphones | ||
| |||
| 10h22 | A One-Vs-One Classifier Ensemble With Majority Voting for Activity Recognition | ||
| |||
| 10h42 | A sparse kernelized matrix learning vector quantization model for human activity recognition | ||
| |||
| 10h43 | A competitive approach for human activity recognition on smartphones | ||
| |||
| 10h44 | Coffee break | ||
| 11h05 | Classification | ||
| 11h05 | A dictionary learning based method for aCGH segmentation | ||
| |||
| 11h25 | A Learning Machine with a Bit-Based Hypothesis Space | ||
| |||
| 11h45 | Optimization by Variational Bounding | ||
| |||
| 12h05 | Classification Poster spotlights | ||
| 12h05 | support vector machine-based aproach for multi-labelers problems | ||
| |||
| 12h06 | Read classification for next generation sequencing | ||
| |||
| 12h07 | A new metric for dissimilarity data classification based on Support Vector Machines optimization | ||
| |||
| 12h08 | DYNG: Dynamic Online Growing Neural Gas for stream data classification | ||
| |||
| 12h09 | Prior knowledge in an end-user trainable machine vision framework | ||
| |||
| 12h10 | Border sensitive fuzzy vector quantization in semi-supervised learning | ||
| |||
| 12h11 | B-bleaching: Agile Overtraining Avoidance in the WiSARD Weightless Neural Classifier | ||
| |||
| 12h12 | WIPS: the WiSARD Indoor Positioning System | ||
| |||
| 12h13 | Cost-sensitive cascade graph neural networks | ||
| |||
| 12h14 | Lunch | ||
| 13h45 | Sparsity for interpretation and visualization in inference models Organized by Vanya Van Belle (Belgium), Paulo Lisboa (UK) | ||
| 13h45 | Research directions in interpretable machine learning models | ||
| |||
| 14h05 | Learning regression models with guaranteed error bounds | ||
| |||
| 14h25 | Sparse approximations for kernel learning vector quantization | ||
| |||
| 14h45 | Robust cartogram visualization of outliers in manifold learning | ||
| |||
| 15h05 | Sparsity for interpretation and visualization in inference models Poster spotlights | ||
| 15h05 | ManiSonS: A New Visualization Tool for Manifold Clustering | ||
| |||
| 15h06 | Visualizing pay-per-view television customers churn using cartograms and flow maps | ||
| |||
| 15h07 | Visualizing dependencies of spectral features using mutual information | ||
| |||
| 15h08 | Coffee break and poster preview | ||
| 17h00 | End of conference | ||