Wednesday April 22, 2009
| 08h30 | Registration | ||
| 09h00 | Opening | ||
| 09h10 | Semi-supervised learning Organized by Antônio de Pádua Braga (Federal Univ. Minas Gerais, Brazil), Tijl De Bie (University of Bristol, United Kingdom), Thiago Turchetti Maia (Vetta Tech, Fed.Univ.Minas Gerais, Brazil) | ||
| 09h10 | Machine Learning with Labeled and Unlabeled Data | ||
| |||
| 09h30 | A Variational Approach to Semi-Supervised Clustering | ||
| |||
| 09h50 | A self-training method for learning to rank with unlabeled data | ||
| |||
| 10h10 | Transductively Learning from Positive Examples Only | ||
| |||
| 10h30 | Supervised classification of categorical data with uncertain labels for DNA barcoding | ||
| |||
| 10h50 | Semi-supervised learning Poster spotlights | ||
| 10h50 | A semi-supervised approach to question classification | ||
| |||
| 10h51 | Improving BAS committee performance with a semi-supervised approach | ||
| |||
| 10h52 | Semi-supervised bipartite ranking with the normalized Rayleigh coefficient | ||
| |||
| 10h53 | Partially-supervised learning in Independent Factor Analysis | ||
| |||
| 10h55 | Coffee break | ||
| 11h15 | Dimensionality reduction | ||
| 11h15 | The Exploration Machine - a novel method for structure-preserving dimensionality reduction | ||
| |||
| 11h35 | Nonlinear Discriminative Data Visualization | ||
| |||
| 11h55 | Does dimensionality reduction improve the quality of motion interpolation? | ||
| |||
| 12h15 | Transformations for variational factor analysis to speed up learning | ||
| |||
| 12h35 | X-SOM and L-SOM: a nested approach for missing value imputation | ||
| |||
| 12h55 | Lunch | ||
| 14h20 | Signal and image processing | ||
| 14h20 | Sparse differential connectivity graph of scalp EEG for epileptic patients | ||
| |||
| 14h40 | Patch-based bilateral filter and local m-smoother for image denoising | ||
| |||
| 15h00 | Adaptive anisotropic denoising: a bootstrapped procedure | ||
| |||
| 15h20 | Learning (with) Preferences Organized by Fabio Aiolli, Alessandro Sperduti (Univ. degli Studi di Padova, Italy | ||
| 15h20 | Supervised learning as preference optimization | ||
| |||
| 15h40 | Efficient voting prediction for pairwise multilabel classification | ||
| |||
| 16h00 | Multi-task Preference learning with Gaussian Processes | ||
| |||
| 16h20 | Poster spotlights | ||
| 16h20 | Adaptive Metrics for Content Based Image Retrieval in Dermatology | ||
| |||
| 16h21 | Bayesian periodogram smoothing for speech enhancement | ||
| |||
| 16h22 | Improving the transition modelling in hidden Markov models for ECG segmentation | ||
| |||
| 16h23 | A robust biologically plausible implementation of ICA-like learning | ||
| |||
| 16h24 | Spline-based neuro-fuzzy Kolmogorov’s network for time series prediction | ||
| |||
| 16h25 | Gene expression data analysis using spatiotemporal blind source separation | ||
| |||
| 16h26 | A wavelet-heterogeneous index of market shocks for assessing the magnitude of financial crises | ||
| |||
| 16h27 | A robust hybrid DHMM-MLP modelling of financial crises measured by the WhIMS | ||
| |||
| 16h28 | A faster model selection criterion for OP-ELM and OP-KNN: Hannan-Quinn criterion | ||
| |||
| 16h29 | Rosen's projection method for SVM training | ||
| |||
| 16h30 | On the huge benefit of quasi-random mutations for multimodal optimization with application to grid-based tuning of neurocontrollers | ||
| |||
| 16h31 | Support vectors machines regression for estimation of mars surface physical properties | ||
| |||
| 16h32 | Self-organising map for large scale processes monitoring | ||
| |||
| 16h33 | The Use of ANN for Turbo Engine Applications | ||
| |||
| 16h34 | Coffee break and poster preview | ||
Thursday April 23, 2009
| 09h00 | Efficient learning in recurrent networks Organized by Benjamin Schrauwen (Ghent University, Belgium), Jochen J. Steil (Bielefeld University, Germany), Barbara Hammer (Clausthal University of Technology, Germany) | ||
| 09h00 | Recent advances in efficient learning of recurrent networks | ||
| |||
| 09h20 | Studies on reservoir initialization and dynamics shaping in echo state networks | ||
| |||
| 09h40 | Non-markovian process modelling with Echo State Networks | ||
| |||
| 10h00 | Stimulus processing and unsupervised learning in autonomously active recurrent networks | ||
| |||
| 10h20 | Reservoir computing for static pattern recognition | ||
| |||
| 10h40 | Efficient learning in recurrent networks Poster spotlights | ||
| 10h40 | Generalisation of action sequences in RNNPB networks with mirror properties | ||
| |||
| 10h41 | Attractor-based computation with reservoirs for online learning of inverse kinematics | ||
| |||
| 10h42 | Coffee break | ||
| 11h00 | Classification and fuzzy logic | ||
| 11h00 | Supervised variable clustering for classification of NIR spectra | ||
| |||
| 11h20 | Fuzzy Fleiss-kappa for Comparison of Fuzzy Classifiers | ||
| |||
| 11h40 | Lukasiewicz fuzzy logic networks and their ultra low power hardware implementation | ||
| |||
| 12h00 | Simultaneous Clustering and Segmentation for Functional Data | ||
| |||
| 12h20 | Lunch | ||
| 13h45 | Neurosciences | ||
| 13h45 | Cerebellum and spatial cognition: A connectionist approach | ||
| |||
| 14h05 | A neural model for binocular vergence control without explicit calculation of disparity | ||
| |||
| 14h25 | Weightless Neural Systems Organized by Massimo De Gregorio (Istituto di Cibernetica-CNR, Italy), Priscila M. V. Lima, Felipe M. G. França (Universidade Federal do Rio de Janeiro, Brazil) | ||
| 14h25 | A brief introduction to Weightless Neural Systems | ||
| |||
| 14h45 | Phenomenal weightless machines | ||
| |||
| 15h05 | Extracting fuzzy rules from “mental” images generated by a modified WISARD perceptron | ||
| |||
| 15h25 | FPGA-based enhanced probabilistic convergent weightless Network for human Iris recognition | ||
| |||
| 15h45 | Weightless Neural Systems Poster spotlights | ||
| 15h45 | Novel Modular Weightless Neural Architectures for Biometrics-based Recognition | ||
| |||
| 15h46 | Quantum RAM Based Neural Netoworks | ||
| |||
| 15h47 | Poster spotlights | ||
| 15h47 | Comparison between linear discrimination analysis and support vector machine for detection of pesticide on spinach leaf by hyperspectral imaging with excitation-emission matrix | ||
| |||
| 15h48 | SVM-based learning method for improving colour adjustment in automotive basecoat manufacturing | ||
| |||
| 15h49 | Application of SVM for cell recognition in BCC skin pathology | ||
| |||
| 15h50 | A neural network model of landmark recognition in the fiddler crab, Uca lactea | ||
| |||
| 15h51 | Classification of high-dimensional data for cervical cancer detection | ||
| |||
| 15h52 | Sparse support vector machines by kernel discriminant analysis | ||
| |||
| 15h53 | Embedding Proximal Support Vectors into Randomized Trees | ||
| |||
| 15h54 | Echo State networks and Neural network Ensembles to predict Sunspots activity | ||
| |||
| 15h55 | Monotonic Recurrent Bounded Derivative Neural Network | ||
| |||
| 15h56 | Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine | ||
| |||
| 15h57 | Connection strategy and performance in sparsely connected 2D associative memory models with non-random images | ||
| |||
| 15h58 | Zero phase-lag synchronization through short-term modulations | ||
| |||
| 15h59 | Learning reconstruction and prediction of natural stimuli by a population of spiking neurons | ||
| |||
| 16h01 | Coffee break and poster preview | ||
Friday April 24, 2009
| 09h00 | Brain Computer Interfaces: from theory to practice Organized by Luc Boullart (Ghent University), Patrick Santens (Ghent University Hospital), Georges Otte (Dr. Guislain Institute), Bart Wyns (Ghent University, Belgium) | ||
| 09h00 | Brain-Computer Interfaces: from theory to practice | ||
| |||
| 09h20 | Oscillation in a network model of neocortex | ||
| |||
| 09h40 | Sensors selection for P300 speller brain computer interface | ||
| |||
| 10h00 | Multiclass brain computer interface based on visual attention | ||
| |||
| 10h20 | Brain Computer Interface for Virtual Reality Control | ||
| |||
| 10h40 | Brain Computer Interfaces: from theory to practice Poster spotlights | ||
| 10h40 | The Possibility of Single-trial Classification of Viewed Characters using EEG Waveforms | ||
| |||
| 10h41 | Exploring the impact of alternative feature representations on BCI classification | ||
| |||
| 10h42 | Uncued brain-computer interfaces: a variational hidden markov model of mental state dynamics | ||
| |||
| 10h43 | Decoding finger flexion using amplitude modulation from band-specific ECoG | ||
| |||
| 10h44 | Neural network pruning for feature selection - Application to a P300 Brain-Computer Interface | ||
| |||
| 10h45 | Augmenting Information from Brain-Computer Interfaces through Bayesian Plan Recognition | ||
| |||
| 10h46 | Coffee break | ||
| 11h05 | Generative and Bayesian models | ||
| 11h05 | Heterogeneous mixture-of-experts for fusion of locally valid knowledge-based submodels | ||
| |||
| 11h25 | Dirichlet process-based component detection in state-space models | ||
| |||
| 11h45 | A variational radial basis function approximation for diffusion processes | ||
| |||
| 12h05 | A regression model with a hidden logistic process for signal parametrization | ||
| |||
| 12h25 | Lunch | ||
| 13h50 | Neural Maps and Learning Vector Quantization - Theory and Applications Organized by Thomas Villmann, Frank-Michael Schleif (Univ. Leipzig, Germany) | ||
| 13h50 | Neural Maps and Learning Vector Quantization - Theory and Applications | ||
| |||
| 14h10 | Hyperparameter Learning in Robust Soft LVQ | ||
| |||
| 14h30 | Median Variant of Fuzzy c-Means | ||
| |||
| 14h50 | Topologically Ordered Graph Clustering via Deterministic Annealing | ||
| |||
| 15h10 | Neural Maps and Learning Vector Quantization - Theory and Applications Poster spotlights | ||
| 15h10 | Equilibrium properties of off-line LVQ | ||
| |||
| 15h11 | Kernelizing Vector Quantization Algorithms | ||
| |||
| 15h12 | A computational framework for exploratory data analysis | ||
| |||
| 15h13 | Poster spotlights | ||
| 15h13 | SOM based methods in early fault detection of nuclear industry | ||
| |||
| 15h14 | Projection of undirected and non-positional graphs using Self Organizing Maps | ||
| |||
| 15h15 | Hardware Implementation Issues of the Neighborhood Mechanism in Kohonen Self Organized Feature Maps | ||
| |||
| 15h16 | Reconciling neural fields to self-organization | ||
| |||
| 15h17 | Applying Mutual Information for Prototype or Instance Selection in Regression Problems | ||
| |||
| 15h18 | Forward feature selection using Residual Mutual Information | ||
| |||
| 15h19 | Gaussian Mixture Models for multiclass problems with performance constraints | ||
| |||
| 15h20 | On the routing complexity of neural network models - Rent's Rule revisited | ||
| |||
| 15h21 | Coffee break and poster preview | ||
| 17h00 | End of conference | ||