Wednesday April 28, 2010
Thursday April 29, 2010
Friday April 30, 2010
| 08h30 | Registration | ||
| 09h00 | Opening | ||
| 09h10 | Supervised and recurrent models | ||
| 09h10 | Efficient online learning of a non-negative sparse autoencoder | ||
| |||
| 09h30 | The Markov Decision Process Extraction Network | ||
| |||
| 09h50 | Maximal Discrepancy for Support Vector Machines | ||
| |||
| 10h10 | Ensemble Modeling with a Constrained Linear System of Leave-One-Out Outputs | ||
| |||
| 10h30 | Financial time series forecasting with machine learning techniques: a survey | ||
| |||
| 10h50 | Coffee break | ||
| 11h10 | Computational Intelligence Business Applications Organized by Thiago Turchetti Maia (Vetta Group, Brazil), Antonio Braga (Univ. Fed. Minas Gerais, Brazil) | ||
| 11h10 | Introduction to Computational Intelligence Business Applications | ||
| |||
| 11h30 | Heuristics Miner for Time Intervals | ||
| |||
| 11h50 | Machine learning analysis and modeling of interest rate curves | ||
| |||
| 12h10 | Modeling contextualized textual knowledge as a Long-Term Working Memory | ||
| |||
| 12h30 | Lunch | ||
| 14h00 | Motion estimation and segmentation | ||
| 14h00 | Neural competition for motion segmentation | ||
| |||
| 14h20 | Adaptive velocity tuning for visual motion estimation | ||
| |||
| 14h40 | Information Visualization, Nonlinear Dimensionality Reduction, Manifold and Topological Learning Organized by Axel Wismüller (Univ. Rochester, New York, USA), John A. Lee, Michel Verleysen (Univ. cat. Louvain, Belgium), Michael Aupetit (CEA, France) | ||
| 14h40 | Recent Advances in Nonlinear Dimensionality Reduction, Manifold and Topological Learning | ||
| |||
| 15h00 | Curvilinear component analysis and Bregman divergences | ||
| |||
| 15h20 | Exploratory Observation Machine (XOM) with Kullback-Leibler Divergence for Dimensionality Reduction and Visualization | ||
| |||
| 15h40 | Adaptive matrix distances aiming at optimum regression subspaces | ||
| |||
| 16h00 | Self Organizing Star (SOS) for health monitoring | ||
| |||
| 16h20 | Information Visualization, Nonlinear Dimensionality Reduction, Manifold and Topological Learning Poster spotlights | ||
| 16h20 | Reliability of dimension reduction visualizations of hierarchical structures | ||
| |||
| 16h21 | Mapping without visualizing local default is nonsense | ||
| |||
| 16h22 | Poster spotlights | ||
| 16h22 | Active set training of support vector regressors | ||
| |||
| 16h23 | Time series input selection using multiple kernel learning | ||
| |||
| 16h24 | Fast and good initialization of RBF networks | ||
| |||
| 16h25 | Least 1-Norm SVMs: a new SVM variant between standard and LS-SVMs | ||
| |||
| 16h26 | An augmented efficient backpropagation training strategy for deep autoassociative neural networks | ||
| |||
| 16h27 | Model Learning from Weights by Adaptive Enhanced Probabilistic Convergent Network | ||
| |||
| 16h28 | Directional predictions for 4-class BCI data | ||
| |||
| 16h29 | Autoregressive independent process analysis with missing observations | ||
| |||
| 16h30 | Combining back-propagation and genetic algorithms to train neural networks for start-up time modeling in combined cycle power plants | ||
| |||
| 16h31 | A new hybrid method between VNS and SEA to improve results on the 0-1 multidimensional knapsack problem | ||
| |||
| 16h32 | A pseudoregression formulation of emphasized soft target procedures for classification problems | ||
| |||
| 16h33 | Exploiting hierarchical prediction structures for mixed 2d-3d tracking | ||
| |||
| 16h34 | Hybrid Soft Computing for PVT Properties Prediction | ||
| |||
| 16h35 | Approximation of chemical reaction rates in turbulent combustion simulation | ||
| |||
| 16h37 | Coffee break and poster preview | ||
Thursday April 29, 2010
| 09h00 | Mixture and generative models | ||
| 09h00 | Exploiting local structure in stacked Boltzmann machines | ||
| |||
| 09h20 | Asymptotic properties of mixture-of-experts models | ||
| |||
| 09h40 | Adaptive learning rate control for "neural gas principal component analysis" | ||
| |||
| 10h00 | Towards sub-quadratic learning of probability density models in the form of mixtures of trees | ||
| |||
| 10h20 | Coffee break | ||
| 10h40 | Sparse representation of data Thomas Villmann (Univ. Applied Sciences Mittweida, Germany), Frank-Michael Schleif (Univ. Leipzig, Germany), Barbara Hammer (Clausthal Univ. Of Tech., Germany) | ||
| 10h40 | Sparse representation of data | ||
| |||
| 11h00 | Highly sparse kernel spectral clustering with predictive out-of-sample extensions | ||
| |||
| 11h20 | Learning sparse codes for image reconstruction | ||
| |||
| 11h40 | Divergence based Learning Vector Quantization | ||
| |||
| 12h00 | Sparse representation of data Poster spotlights | ||
| 12h00 | Finding correlations in multimodal data using decomposition approaches | ||
| |||
| 12h01 | Geometric models with co-occurrence groups | ||
| |||
| 12h02 | Deep learning of visual control policies | ||
| |||
| 12h03 | Learning vector quantization for heterogeneous structured data | ||
| |||
| 12h04 | Relational Generative Topographic Map | ||
| |||
| 12h05 | Lunch | ||
| 13h35 | Physiology and learning | ||
| 13h35 | Neural oscillations allow for selective inhibition - New perspective on the role of cortical gamma oscillations | ||
| |||
| 13h55 | Learning how to grasp objects | ||
| |||
| 14h15 | Machine learning techniques based on random projections Organized by Benjamin Schrauwen (Ghent Univ., Belgium), Amaury Lendasse (Helsinki Univ. of Tech., Finland), Yoan Miche (I.N.P. Grenoble, France) | ||
| 14h15 | Machine Learning Techniques based on Random Projections | ||
| |||
| 14h35 | Extending reservoir computing with random static projections: a hybrid between extreme learning and RC | ||
| |||
| 14h55 | Solving Large Regression Problems using an Ensemble of GPU-accelerated ELMs | ||
| |||
| 15h15 | Using SVMs with randomised feature spaces: an extreme learning approach | ||
| |||
| 15h35 | Machine learning techniques based on random projections Poster spotlights | ||
| 15h35 | A Markovian characterization of redundancy in echo state networks by PCA | ||
| |||
| 15h36 | Random search enhancement of error minimized extreme learning machine | ||
| |||
| 15h37 | TreeESN: a Preliminary Experimental Analysis | ||
| |||
| 15h38 | Poster spotlights | ||
| 15h38 | A novel interactive biometric passport photograph alignment system | ||
| |||
| 15h39 | Oriented Bounding Box Computation Using Particle Swarm Optimization | ||
| |||
| 15h40 | Identifying informative features for ERP speller systems based on RSVP paradigm | ||
| |||
| 15h41 | Predicting spike-timing of a thalamic neuron using a stochastic synaptic model | ||
| |||
| 15h42 | Modelling the McGurk effect | ||
| |||
| 15h43 | A critique of BCM behavior verification for STDP-type plasticity models | ||
| |||
| 15h47 | Coffee break and poster preview | ||
Friday April 30, 2010
| 09h00 | Unsupervised learning | ||
| 09h00 | An automated SOM clustering based on data topology | ||
| |||
| 09h20 | A randomized algorithm for spectral clustering | ||
| |||
| 09H40 | Relevance learning in generative topographic maps | ||
| |||
| 10h00 | Multiple Local Models for System Identification Using Vector Quantization Algorithms | ||
| |||
| 10h20 | Extending FSNPC to handle data points with fuzzy class assignments | ||
| |||
| 10h40 | Coffee break | ||
| 11h00 | Image and video analysis | ||
| 11h00 | Principal curve tracing | ||
| |||
| 11h20 | Mode estimation in high-dimensional spaces with flat-top kernels: application to image denoising | ||
| |||
| 11h40 | Figure-ground Segmentation using Metrics Adaptation in Level Set Methods | ||
| |||
| 12h00 | An ART-type network approach for video object detection | ||
| |||
| 12h20 | Lunch | ||
| 13h40 | Computational Intelligence in Biomedicine Organized by Paulo J.G. Lisboa (Liverpool John Moores Univ., U.K.), Alfredo Vellido (Tech. Univ. Catalonia, Spain), José D. Martín (Univ. Valencia, Spain) | ||
| 13h40 | Computational Intelligence in biomedicine: Some contributions | ||
| |||
| 14h00 | Segmentation of EMG time series using a variational Bayesian approach for the robust estimation of cortical silent periods | ||
| |||
| 14h20 | Spectral Prototype Extraction for dimensionality reduction in brain tumour diagnosis | ||
| |||
| 14h40 | On the use of a clinical kernel in survival analysis | ||
| |||
| 15h00 | Computational Intelligence in Biomedicine Poster spotlights | ||
| 15h00 | The Application of Gaussian Processes in the Prediction of Percutaneous Absorption for Mammalian and Synthetic Membranes | ||
| |||
| 15h01 | Neural models for the analysis of kidney disease patients | ||
| |||
| 15h02 | Poster spotlights | ||
| 15h02 | Distance functions for local PCA methods | ||
| |||
| 15h03 | KNN behavior with set-valued attributes | ||
| |||
| 15h04 | Kernel generative topographic mapping | ||
| |||
| 15h05 | On Finding Complementary Clusterings | ||
| |||
| 15h06 | Consensus clustering by graph based approach | ||
| |||
| 15h07 | Web Document Clustering based on a Hierarchical Self-Organizing Model | ||
| |||
| 15h08 | Online speaker diarization with a size-monitored growing neural gas algorithm | ||
| |||
| 15h09 | Validation of unsupervised clustering methods for leaf phenotype screening | ||
| |||
| 15h10 | A Novel Two-Phase SOM Clustering Approach to Discover Visitor Interests in a Website | ||
| |||
| 15h11 | Image registration by the extended evolutionary self-organizing map | ||
| |||
| 15h12 | Programmable triangular neighborhood functions of Kohonen Self-Organizing Maps realized in CMOS technology | ||
| |||
| 15h13 | Evolution of adaptive center-crossing continuous time recurrent neural networks for biped robot control | ||
| |||
| 15h14 | Free-energy-based reinforcement learning in a partially observable environment | ||
| |||
| 15h15 | A New Error-Correcting Decoder with Retransmit Signal Implemented with a Hardlimit Neural Network | ||
| |||
| 15h16 | Coffee break and poster preview | ||
| 16h30 | End of conference | ||