Wednesday April 23, 2014
Thursday April 24, 2014b>
Friday April 25, 2014
| 08h30 | Registration | ||
| 09h00 | Opening | ||
| 09h10 | Advances in Spiking Neural Information Processing Systems (SNIPS) Organized by Sander Bohte (Netherlands), Andre Gruning (UK) | ||
| 09h10 | Spiking Neural Networks: Principles and Challenges | ||
| |||
| 09h30 | A new biologically plausible supervised learning method for spiking neurons | ||
| |||
| 09h50 | Spiking AGREL | ||
| |||
| 10h10 | Advances in Spiking Neural Information Processing Systems (SNIPS) Poster spotlights | ||
| 10h10 | Classifying Patterns in a Spiking Neural Network | ||
| |||
| 10h11 | Toward STDP-based population action in large networks of spiking neurons | ||
| |||
| 10h12 | Vector quantization- and nearest neighbour-based methods | ||
| 10h12 | Supervised Generative Models for Learning Dissimilarity Data | ||
| |||
| 10h32 | Rejection strategies for learning vector quantization | ||
| |||
| 10h52 | Vector quantization- and nearest neighbour-based methods Poster spotlights | ||
| 10h52 | Optimization of General Statistical Accuracy Measures for Classification Based on Learning Vector Quantization | ||
| |||
| 10h53 | Augmented hashing for semi-supervised scenarios | ||
| |||
| 10h54 | Improving accuracy by reducing the importance of hubs in nearest-neighbor recommendations | ||
| |||
| 10h55 | A new approach for multiple instance learning based on a homogeneity bag operator | ||
| |||
| 10h56 | Coffee break | ||
| 11h15 | Byte the bullet: learning on real-world computing architectures Organized by Davide Anguita, Alessandro Ghio, Luca Oneto (Italy) | ||
| 11h15 | Byte The Bullet: Learning on Real-World Computing Architectures | ||
| |||
| 11h35 | Learning with few bits on small-scale devices: From regularization to energy efficiency | ||
| |||
| 11h55 | Speedy greedy feature selection: Better redshift estimation via massive parallelism | ||
| |||
| 12h15 | Context- and cost-aware feature selection in ultra-low-power sensor interfaces | ||
| |||
| 12h35 | Byte the bullet: learning on real-world computing architectures Poster spotlights | ||
| 12h35 | Lightning fast asynchronous distributed k-means clustering | ||
| |||
| 12h36 | Lunch | ||
| 14h00 | Reinforcement learning and optimization | ||
| 14h00 | Selective Neural Network Ensembles in Reinforcement Learning | ||
| |||
| 14h20 | Learning resets of neural working memory | ||
| |||
| 14h40 | Reinforcement learning and optimization Poster spotlights | ||
| 14h40 | Naive Augmenting Q-Learning to Process Feature-Based Representations of States | ||
| |||
| 14h41 | Direct Model-Predictive Control | ||
| |||
| 14h42 | Ensembles of extreme learning machine networks for value prediction | ||
| |||
| 14h43 | An application of the temporal difference algorithm to the truck backer-upper problem | ||
| |||
| 14h44 | Application of Newton's Method to action selection in continuous state- and action-space reinforcement learning | ||
| |||
| 14h45 | Linear Scalarized Knowledge Gradient in the Multi-Objective Multi-Armed Bandits Problem | ||
| |||
| 14h46 | Improving the firefly algorithm through the Barnes-Hut tree code | ||
| |||
| 14h47 | Improved Cat Swarm Optimization approach applied to reliability-redundancy problem | ||
| |||
| 14h48 | Nonlinear dimensionality reduction | ||
| 14h48 | Relevance Learning for Dimensionality Reduction | ||
| |||
| 15h08 | Dimensionality reduction in decentralized networks by Gossip aggregation of principal components analyzers | ||
| |||
| 15h28 | Multiscale stochastic neighbor embedding: Towards parameter-free dimensionality reduction | ||
| |||
| 15h48 | Nonlinear dimensionality reduction Poster spotlights | ||
| 15h48 | Interactive dimensionality reduction for visual analytics | ||
| |||
| 15h49 | Recent methods for dimensionality reduction: A brief comparative analysis | ||
| |||
| 15h50 | Signal and temporal processing | ||
| 15h50 | Capturing confounding sources of variation in DNA methylation data by spatiotemporal independent component analysis | ||
| |||
| 16h10 | Towards an effective multi-map self organizing recurrent neuronal network | ||
| |||
| 16h30 | Signal and temporal processing Poster spotlights | ||
| 16h30 | Iterative ARIMA-multiple support vector regression models for long term time series prediction | ||
| |||
| 16h31 | Region of interest detection using MLP | ||
| |||
| 16h32 | Analysis of the Weighted Fuzzy C-means in the problem of source location | ||
| |||
| 16h33 | An Optimized Learning Algorithm Based on Linear Filters Suitable for Hardware implemented Self-Organizing Maps | ||
| |||
| 16H34 | Enhanced NMF initialization using a physical model for pollution source apportionment | ||
| |||
| 16h35 | A New Error-Correcting Syndrome Decoder with Retransmit Signal Implemented with an Hardlimit Neural Network | ||
| |||
| 16h36 | Coffee break and poster preview | ||
Thursday April 24, 2014b>
| 09h00 | Learning of structured and non-standard data Organized by Frank-Michael Schleif, Thomas Villmann, Peter Tino (Germany & UK) | ||
| 09h00 | Recent trends in learning of structured and non-standard data | ||
| |||
| 09h20 | Support Vector Ordinal Regression using Privileged Information | ||
| |||
| 09h40 | Segmented shape-symbolic time series representation | ||
| |||
| 10h00 | Adaptive distance measures for sequential data | ||
| |||
| 10h20 | Learning of structured and non-standard data Poster spotlights | ||
| 10h20 | Applications of lp-Norms and their Smooth Approximations for Gradient Based Learning Vector Quantization | ||
| |||
| 10h21 | Utilization of Chemical Structure Information for Analysis of Spectra Composites | ||
| |||
| 10h22 | Weighted tree kernels for sequence analysis | ||
| |||
| 10h23 | Coffee break | ||
| 10h45 | Kernel methods | ||
| 10h45 | Easy multiple kernel learning | ||
| |||
| 11h05 | Joint SVM for Accurate and Fast Image Tagging | ||
| |||
| 11h25 | Kernel methods for mixed feature selection | ||
| |||
| 11h45 | The one-sided mean kernel: a positive definite kernel for time series | ||
| |||
| 12h05 | A robust regularization path for the Doubly Regularized Support Vector Machine | ||
| |||
| 12h25 | Kernel methods Poster spotlights | ||
| 12h25 | Tensor decomposition of dense SIFT descriptors in object recognition | ||
| |||
| 12h26 | Fine-tuning of support vector machine parameters using racing algorithms | ||
| |||
| 12h27 | reject option paradigm for the reduction of support vectors | ||
| |||
| 12h28 | The Choquet kernel for monotone data | ||
| |||
| 12h29 | Lunch | ||
| 13h50 | Learning and Modeling Big Data Organized by Barbara Hammer, Haibo He, Thomas Martinetz (Germany & USA) | ||
| 13h50 | Learning and modeling big data | ||
| |||
| 14h10 | Agglomerative hierarchical kernel spectral clustering for large scale networks | ||
| |||
| 14h30 | Proximity learning for non-standard big data | ||
| |||
| 14h50 | Learning and Modeling Big Data Poster spotlights | ||
| 14h50 | Predicting Grain Protein Content of Winter Wheat | ||
| |||
| 14h51 | Classification | ||
| 14h51 | On the complexity of shallow and deep neural network classifiers | ||
| |||
| 15h11 | Evidence build-up facilitates on-line adaptivity in dynamic environments: example of the BCI P300-speller | ||
| |||
| 15h31 | Choosing the Metric in High-Dimensional Spaces Based on Hub Analysis | ||
| |||
| 15h51 | Robust outlier detection with L0-SVDD | ||
| |||
| 16h11 | Classification Poster spotlights | ||
| 16h11 | Toward parallel feature selection from vertically partitioned data | ||
| |||
| 16h12 | Modeling consumption of contents and advertising in online newspapers | ||
| |||
| 16h13 | Reweighted l1 Dual Averaging Approach for Sparse Stochastic Learning | ||
| |||
| 16h14 | Using Shannon Entropy as EEG Signal Feature for Fast Person Identification | ||
| |||
| 16h15 | Machine learning techniques to assess the performance of a gait analysis system | ||
| |||
| 16h16 | A Random Forest proximity matrix as a new measure for gene annotation | ||
| |||
| 16h17 | Neural network based 2D/3D fusion for robotic object recognition | ||
| |||
| 16h18 | Discrimination of visual pedestrians data by combining projection and prediction learning | ||
| |||
| 16h19 | FINGeR: Framework for interactive neural-based gesture recognition | ||
| |||
| 16h20 | Beyond histograms: why learned structure-preserving descriptors outperform HOG | ||
| |||
| 16h21 | NMF-Density: NMF-Based Breast Density Classifier | ||
| |||
| 16h22 | Dynamical systems and online learning | ||
| 16h22 | Implicitly and explicitly constrained optimization problems for training of recurrent neural networks | ||
| |||
| 16h42 | A HMM-based pre-training approach for sequential data | ||
| |||
| 17h02 | Dynamical systems and online learning Poster spotlights | ||
| 17h02 | Exploiting similarity in system identification tasks with recurrent neural networks | ||
| |||
| 17h04 | Comparison of local and global undirected graphical models | ||
| |||
| 17h05 | Meta Online Learning: Experiments on a Unit Commitment Problem | ||
| |||
| 17h06 | DELA: A Dynamic Online Ensemble Learning Algorithm | ||
| |||
| 17h07 | Coffee break and poster preview | ||
Friday April 25, 2014
| 09h00 | Advances on Weightless Neural Systems Organized by Massimo De Gregorio, Priscila M.V. Lima, Wilson R. de Oliveira (Italy & Brazil) | ||
| 09h00 | Advances on Weightless Neural Systems | ||
| |||
| 09h20 | Learning state prediction using a weightless neural explorer | ||
| |||
| 09h40 | Can you follow that guy? | ||
| |||
| 10h00 | Credit analysis with a clustering RAM-based neural classifier | ||
| |||
| 10h20 | Training a classical weightless neural network in a quantum computer | ||
| |||
| 10h40 | Advances on Weightless Neural Systems Poster spotlights | ||
| 10h40 | Extracting rules from DRASiW’s "mental images" | ||
| |||
| 10h41 | Vector space weightless neural networks | ||
| |||
| 10h42 | Online tracking of multiple objects using WiSARD | ||
| |||
| 10h43 | Probabilistic automata simulation with single layer weightless neural networks | ||
| |||
| 10h44 | Coffee break | ||
| 11h05 | Clustering | ||
| 11h05 | Optimal Data Projection for Kernel Spectral Clustering | ||
| |||
| 11h25 | Supporting GNG-based clustering with local input space histograms | ||
| |||
| 11h45 | The Sum-over-Forests clustering | ||
| |||
| 12h05 | Clustering Poster spotlights | ||
| 12h05 | Bayesian non-parametric parsimonious clustering | ||
| |||
| 12h06 | Learning predictive partitions for continuous feature spaces | ||
| |||
| 12h07 | An adjustable p-exponential clustering algorithm | ||
| |||
| 12h08 | Self-organizing map for determination of goal candidates in mobile robot exploration | ||
| |||
| 12h09 | Regression, Forceasting and Extreme Learning Machines | ||
| 12h09 | Parameter-free regularization in Extreme Learning Machines with affinity matrices | ||
| |||
| 12h29 | Regression, Forceasting and Extreme Learning Machines Poster spotlights | ||
| 12h29 | Feature selection in environmental data mining combining Simulated Annealing and Extreme Learning Machine | ||
| |||
| 12h30 | Mobility Prediction Using Fully-Complex Extreme Learning Machines | ||
| |||
| 12h31 | An Extreme Learning Approach to Active Learning | ||
| |||
| 12h32 | A new model selection approach for the ELM network using metaheuristic optimization | ||
| |||
| 12h33 | Extreme learning machines for Internet traffic classification | ||
| |||
| 12h34 | Electric load forecasting using wavelet transform and extreme learning machine | ||
| |||
| 12h35 | Swim velocity profile identification through a Dynamic Self-adaptive Multiobjective Harmonic Search and RBF neural networks | ||
| |||
| 12h36 | Dynamic ensemble selection and instantaneous pruning for regression | ||
| |||
| 12h37 | Data normalization and supervised learning to assess the condition of patients with multiple sclerosis based on gait analysis | ||
| |||
| 12h38 | Sparse one hidden layer MLPs | ||
| |||
| 12h39 | Multi-Step Ahead Forecasting of Road Condition Using Least Squares Support Vector Regression | ||
| |||
| 12h40 | Lunch | ||
| 14h00 | Label noise in classification Organized by Benoît Frénay, Ata Kaban (Belgium and UK) | ||
| 14h00 | A comprehensive introduction to label noise | ||
| |||
| 14h20 | Improving the Robustness of Bagging with Reduced Sampling Size | ||
| |||
| 14h40 | Credal decision trees in noisy domains | ||
| |||
| 15h00 | Finding Originally Mislabels with MD-ELM | ||
| |||
| 15h20 | Label noise in classification Poster spotlights | ||
| 15h20 | Misclassification of class C G-protein-coupled receptors as a label noise problem | ||
| |||
| 15h21 | A multi-class extension for multi-labeler support vector machines | ||
| |||
| 15h23 | Coffee break and poster preview | ||
| 17h00 | End of conference | ||