Wednesday April 27, 2011
Thursday April 28, 2011
Friday April 29, 2011
| 08h30 | Registration | ||
| 09h00 | Opening | ||
| 09h10 | Information theory related learning Organized by Thomas Villmann (Univ. of Apllied Sciences Mittweida, Germany), Andrzej Cichocki (Riken, Japan), Jose Principe (Univ. of Florida, USA) | ||
| 09h10 | Information theory related learning | ||
| |||
| 09h30 | Optimization of Parametrized Divergences in Fuzzy c-Means | ||
| |||
| 09h50 | Multivariate class labeling in Robust Soft LVQ | ||
| |||
| 10h10 | Statistical dependence measure for feature selection in microarray datasets | ||
| |||
| 10h30 | Mathematical Foundations of the Self Organized Neighbor Embedding (SONE) for Dimension Reduction and Visualization | ||
| |||
| 10h50 | Coffee break | ||
| 11h10 | Self-organizing maps and recurrent networks | ||
| 11h10 | Sparsity Issues in Self-Organizing-Maps for Structures | ||
| |||
| 11h30 | Multi-Goal Path Planning Using Self-Organizing Map with Navigation Functions | ||
| |||
| 11h50 | Statistical properties of the `Hopfield estimator' of dynamical systems | ||
| |||
| 12h10 | Negatively Correlated Echo State Networks | ||
| |||
| 12h30 | Reservoir regularization stabilizes learning of Echo State Networks with output feedback | ||
| |||
| 12h50 | Lunch | ||
| 14h20 | Semi-supervised learning | ||
| 14h20 | A Multi-kernel Framework for Inductive Semi-supervised Learning | ||
| |||
| 14h40 | Training of multiple classifier systems utilizing partially labeled sequential data sets | ||
| |||
| 15h00 | Computational Intelligence in Life Sciences Organized by Frank-Michael Schleif (Univ. of Bielefeld), Udo Seiffert (Fraunhofer IFF & Univ. of Magdeburg), Dietlind Zühlke (Fraunhofer FIT, St. Augustin, Germany) | ||
| 15h00 | Recent trends in computational intelligence in life sciences | ||
| |||
| 15h20 | Adaptive Kernel Smoothing Regression for Spatio-Temporal Environmental Datasets | ||
| |||
| 15h40 | Generalized functional relevance learning vector quantization | ||
| |||
| 16h00 | Patch Affinity Propagation | ||
| |||
| 16h20 | Computational Intelligence in Life Sciences Poster spotlights | ||
| 16h20 | Multispectral image characterization by partial generalized covariance | ||
| |||
| 16h21 | Poster spotlights | ||
| 16h21 | Increased robustness and intermittent dynamics in structured Reservoir Networks with feedback | ||
| |||
| 16h22 | Anticipating Rewards in Continuous Time and Space with Echo State Networks and Actor-Critic Design | ||
| |||
| 16h23 | Application of stochastic recurrent reinforcement learning to index trading | ||
| |||
| 16h24 | A brief tutorial on reinforcement learning: The game of Chung Toi | ||
| |||
| 16h25 | D-VisionDraughts: a draughts player neural network that learns by reinforcement in a high performance environment | ||
| |||
| 16h26 | SO-VAT: Self-Organizing Visual Assessment of cluster Tendency for large data sets | ||
| |||
| 16h27 | New conditioning model for robots | ||
| |||
| 16h28 | Stability of Neural Network Control for Uncertain Sampled-Data Systems | ||
| |||
| 16h29 | Thresholds tuning of a neuro-symbolic net controlling a behavior-based robotic system | ||
| |||
| 16h30 | Ensemble Usage for More Reliable Policy Identification in Reinforcement Learning | ||
| |||
| 16h32 | Fisherman learning algorithm of the SOM realized in the CMOS technology | ||
| |||
| 16h33 | Abstract category learning | ||
| |||
| 16h34 | Symbolic computing of LS-SVM based models | ||
| |||
| 16h35 | Sparse LS-SVMs with L0?norm minimization | ||
| |||
| 16h36 | A post-processing strategy for SVM learning from unbalanced data | ||
| |||
| 16h37 | Clustering data streams with weightless neural networks | ||
| |||
| 16h38 | Locating Anomalies Using Bayesian Factorizations and Masks | ||
| |||
| 16h39 | Comparison of the Complex Valued and Real Valued Neural Networks Trained with Gradient Descent and Random Search Algorithms | ||
| |||
| 16h40 | Coffee break and poster preview | ||
Thursday April 28, 2011
| 09h00 | Seeing is believing: The importance of visualization in real-world machine learning applications Organized by Alfredo Vellido (Technical Univ. of Catalonia, Spain), José D. Martín (Univ. of Valencia, Spain), Paulo J. G. Lisboa (Liverpool John Moores | ||
| 09h00 | Seeing is believing: The importance of visualization in real-world machine learning applications | ||
| |||
| 09h20 | Hierarchical clustering for graph visualization | ||
| |||
| 09h40 | A probabilistic approach to the visual exploration of G Protein-Coupled Receptor sequences | ||
| |||
| 10h00 | Growing Hierarchical Sectors on Sectors | ||
| |||
| 10h20 | Seeing is believing: The importance of visualization in real-world machine learning applications Poster spotlights | ||
| 10h20 | Analysis of a Reinforcement Learning algorithm using Self-Organizing Maps | ||
| |||
| 10h21 | Coffee break | ||
| 10h40 | Learning theory | ||
| 10h40 | General bound of overfitting for MLP regression models | ||
| |||
| 11h00 | Maximal Discrepancy vs. Rademacher Complexity for error estimation | ||
| |||
| 11h20 | Feature selection and dimensionality reduction | ||
| 11h20 | Class-Specific Feature Selection for One-Against-All Multiclass SVMs | ||
| |||
| 11h40 | Mutual information for feature selection with missing data | ||
| |||
| 12h00 | Probabilistic Fisher discriminant analysis | ||
| |||
| 12h20 | Supervised dimension reduction mappings | ||
| |||
| 12h40 | Lunch | ||
| 14h10 | Learning of causal relations Organized by Michael Biehl (Univ. of Groningen), Tom Heskes (Radboud Univ. Nijmegen, The Netherlands), Joris Mooij (MPI for Biological Cybernetics, Tübingen, Germany), John Quinn (Makerere Univ., Kampala, Uganda) | ||
| 14h10 | Learning of causal relations | ||
| |||
| 14h30 | Inferring the causal decomposition under the presence of deterministic relations | ||
| |||
| 14h50 | A unified approach to estimation and control of the False Discovery Rate in Bayesian network skeleton identification | ||
| |||
| 15h10 | A structure independent algorithm for causal discovery | ||
| |||
| 15h30 | Causal relevance learning for robust classification under interventions | ||
| |||
| 15h50 | Learning of causal relations Poster spotlights | ||
| 15h50 | A constraint-based approach to incorporate prior knowledge in causal models | ||
| |||
| 15h51 | Poster spotlights | ||
| 15h51 | Selecting from an infinite set of features in SVM | ||
| |||
| 15h52 | Mutual information based feature selection for mixed data | ||
| |||
| 15h53 | Unsupervised feature selection for sparse data | ||
| |||
| 15h54 | Multi-class classification in the presence of labelling errors | ||
| |||
| 15h55 | Principal component analysis for unsupervised calibration of bio-inspired airflow array sensors | ||
| |||
| 15h56 | Effects of sparseness and randomness of pairwise distance matrix on t-SNE results | ||
| |||
| 15h57 | Nearest neighbors and correlation dimension for dimensionality estimation. Application to factor analysis of real biological time series data. | ||
| |||
| 15h58 | A Similarity Function with Local Feature Weighting for Structured Data | ||
| |||
| 15h59 | Exploiting vertices states in GraphESN by weighted nearest neighbor | ||
| |||
| 16h00 | The role of Fisher information in primary data space for neighbourhood mapping | ||
| |||
| 16h01 | Communication Challenges in Cloud K-means | ||
| |||
| 16h02 | A Spectral Based Clustering Algorithm for Categorical Data with Maximum Modularity | ||
| |||
| 16h03 | Single-trial P300 detection with Kalman filtering and SVMs | ||
| |||
| 16h04 | Classifying mental states with machine learning algorithms using alpha activity decline | ||
| |||
| 16h05 | Approaches for Automatic Speaker Recognition in a Binaural Humanoid Context | ||
| |||
| 16h06 | Fast Data Mining with Sparse Chemical Graph Fingerprints by Estimating the Probability of Unique Patterns | ||
| |||
| 16h07 | Automatic Enhancement of Correspondence Detection in an Object Tracking System | ||
| |||
| 16h08 | Coffee break and poster preview | ||
Friday April 29, 2011
| 09h00 | Sequence and time processing | ||
| 09h00 | Time Experiencing by Robotic Agents | ||
| |||
| 09h20 | Visual place recognition using Bayesian filtering with Markov chains | ||
| |||
| 09h40 | Iterative multi-task sequence labeling for predicting structural properties of proteins | ||
| |||
| 10h00 | Identification of sparse spatio-temporal features in Evoked Response Potentials | ||
| |||
| 10h20 | Hybrid HMM and HCRF model for sequence classification | ||
| |||
| 10h40 | A Neural Filter for Electrolocation in Weakly Electric Fish | ||
| |||
| 11h00 | Coffee break | ||
| 11h20 | Optimization and learning | ||
| 11h20 | Non-linearly increasing resampling in racing algorithms | ||
| |||
| 11h40 | A distributed learning algorithm based on two-layer artificial neural networks and genetic algorithms | ||
| |||
| 12h00 | Deep Learning Organized by Hélène Paugam-Moisy (Univ. de Lyon), Sébastien Rebecchi, Sylvain Chevallier (INRIA Saclay), Ludovic Arnold (Univ. Paris-Sud 11, France) | ||
| 12h00 | An Introduction to Deep Learning | ||
| |||
| 12h20 | Using very deep autoencoders for content-based image retrieval | ||
| |||
| 12h40 | Training RBMs based on the signs of the CD approximation of the log-likelihood derivatives | ||
| |||
| 13h00 | A supervised strategy for deep kernel machine | ||
| |||
| 13h20 | Lunch | ||
| 14h50 | End of conference | ||