Wednesday 27 April 2016
| 09h00 | Opening | ||
| 09h10 | Advances in Learning with Kernels: Theory and Practice in a World of growing Constraints Organized by Luca Oneto, Davide Anguita, Fabio Aiolli, Michele Donini, Nicol? Navarin (Italy) | ||
| 09h10 | Advances in Learning with Kernels: Theory and Practice in a World of growing Constraints | ||
| |||
| 09h30 | Kernel based collaborative filtering for very large scale top-N item recommendation | ||
| |||
| 09h50 | RNAsynth: constraints learning for RNA inverse folding. | ||
| |||
| 10h10 | Measuring the Expressivity of Graph Kernels through the Rademacher Complexity | ||
| |||
| 10h30 | A reservoir activation kernel for trees | ||
| |||
| 10h50 | Advances in Learning with Kernels: Theory and Practice in a World of growing Constraints Poster spotlights | ||
| 10h50 | Learning with hard constraints as a limit case of learning with soft constraints | ||
| |||
| 10h51 | Gaussian process prediction for time series of structured data | ||
| |||
| 10h52 | Efficient low rank approximation via alternating least squares for scalable kernel learning | ||
| |||
| 10h53 | Coffee break | ||
| 11h15 | Regression and mathematical models | ||
| 11h15 | Modelling of parameterized processes via regression in the model space | ||
| |||
| 11h35 | Auto-adaptive Laplacian Pyramids | ||
| |||
| 11h55 | Using Robust Extreme Learning Machines to Predict Cotton Yarn Strength and Hairiness | ||
| |||
| 12h15 | RSS-based Robot Localization in Critical Environments using Reservoir Computing | ||
| |||
| 12h35 | Regression and mathematical models Poster spotlights | ||
| 12h35 | Interpretability of machine learning models and representations: an introduction | ||
| |||
| 12h36 | Bayesian mixture of spatial spline regressions | ||
| |||
| 12h37 | Comparison of three algorithms for parametric change-point detection | ||
| |||
| 12h38 | Differentiable piecewise-B?zier interpolation on Riemannian manifolds | ||
| |||
| 12h39 | Extending a two-variable mean to a multi-variable mean | ||
| |||
| 12h40 | neuro-percolation as a superposition of random-walks | ||
| |||
| 12h41 | Lunch | ||
| 14h05 | Indefinite proximity learning Organized by Frank-Michael Schleif, Peter Tino (UK), Yingyu Liang (USA) | ||
| 14h05 | Learning in indefinite proximity spaces - recent trends | ||
| |||
| 14h25 | Discriminative dimensionality reduction in kernel space | ||
| |||
| 14h45 | Indefinite proximity learning Poster spotlights | ||
| 14h45 | Study on the loss of information caused by the "positivation" of graph kernels for 3D shapes | ||
| |||
| 14h46 | Adaptive dissimilarity weighting for prototype-based classification optimizing mixtures of dissimilarities | ||
| |||
| 14h47 | Deep learning, text, image and signal processing | ||
| 14h47 | Deep multi-task learning with evolving weights | ||
| |||
| 15h07 | Deep neural network analysis of go games: which stones motivate a move? | ||
| |||
| 15h27 | Feature binding in deep convolution networks with recurrences, oscillations, and top-down modulated dynamics | ||
| |||
| 15h47 | Maximum likelihood learning of RBMs with Gaussian visible units on the Stiefel manifold | ||
| |||
| 16h07 | Deep learning, text, image and signal processing Poster spotlights | ||
| 16h07 | Semi-Supervised Classification of Social Textual Data Using WiSARD | ||
| |||
| 16h08 | On the equivalence between algorithms for Non-negative Matrix Factorization and Latent Dirichlet Allocation | ||
| |||
| 16h09 | Word Embeddings for Morphologically Rich Languages | ||
| |||
| 16h10 | Localized discriminative Gaussian process latent variable model for text-dependent speaker verification | ||
| |||
| 16h11 | Multi-task learning for speech recognition: an overview | ||
| |||
| 16h12 | Bayesian semi non-negative matrix factorisation | ||
| |||
| 16h13 | An Immune-Inspired, Dependence-Based Approach to Blind Inversion of Wiener Systems | ||
| |||
| 16h14 | A new penalisation term for image retrieval in clique neural networks | ||
| |||
| 16h15 | Gesture Recognition with a Convolutional Long Short-Term Memory Recurrent Neural Network | ||
| |||
| 16h17 | Coffee break and poster exhibition | ||
Thursday 28 April 2016
| 09h00 | Machine learning for medical applications Organized by Ver?nica Bol?n-Canedo, Amparo Alonso-Betanzos (Spain), Beatriz Remeseiro, Aur?lio Campilho (Portugal) | ||
| 09h00 | Machine learning for medical applications | ||
| |||
| 09h20 | Automatic detection of EEG arousals | ||
| |||
| 09h40 | Stacked denoising autoencoders for the automatic recognition of microglial cells? state | ||
| |||
| 10h00 | A machine learning pipeline for supporting differentiation of glioblastomas from single brain metastases | ||
| |||
| 10h20 | Feature definition, analysis and selection for lung nodule classification in chest computerized tomography images | ||
| |||
| 10h40 | Bag-of-Steps: predicting lower-limb fracture rehabilitation length | ||
| |||
| 11h00 | Machine learning for medical applications Poster spotlights | ||
| 11h00 | Initializing nonnegative matrix factorization using the successive projection algorithm for multi-parametric medical image segmentation | ||
| |||
| 11h01 | On the analysis of feature selection techniques in a conjunctival hyperemia grading framework | ||
| |||
| 11h02 | Using a feature selection ensemble on DNA microarray datasets | ||
| |||
| 11h03 | A fast learning algorithm for high dimensional problems: an application to microarrays | ||
| |||
| 11h04 | Data complexity measures for analyzing the effect of SMOTE over microarrays | ||
| |||
| 11h05 | Multi-step strategy for mortality assessment in cardiovascular risk patients with imbalanced data | ||
| |||
| 11h06 | Spatiotemporal ICA improves the selection of differentially expressed genes | ||
| |||
| 11h07 | Unsupervised Cross-Subject BCI Learning and Classification using Riemannian Geometry | ||
| |||
| 11h08 | Assessment of diabetic retinopathy risk with random forests | ||
| |||
| 11h09 | Coffee break | ||
| 11h30 | Physics and Machine Learning: Emerging Paradigms Organized by Jos? D. Mart?n-Guerrero (Spain), Paulo J. G. Lisboa (UK), Alfredo Vellido (Spain) | ||
| 11h30 | Physics and Machine Learning: Emerging Paradigms | ||
| |||
| 11h50 | Controlling adaptive quantum-phase estimation with scalable reinforcement learning | ||
| |||
| 12h10 | How machine learning won the Higgs boson challenge | ||
| |||
| 12h30 | Physics and Machine Learning: Emerging Paradigms Poster spotlights | ||
| 12h30 | Performance assessment of quantum clustering in non-spherical data distributions | ||
| |||
| 12h31 | Supervised quantum gate "teaching" for quantum hardware design | ||
| |||
| 12h32 | Enhanced learning for agents in quantum-accessible environments | ||
| |||
| 12h33 | Lunch | ||
| 14h00 | Incremental learning algorithms and applications Organized by Alexander Gepperth (France), Barbara Hammer (Germany) | ||
| 14h00 | Incremental learning algorithms and applications | ||
| |||
| 14h20 | Choosing the best algorithm for an incremental on-line learning task | ||
| |||
| 14h40 | Incremental learning algorithms and applications Poster spotlights | ||
| 14h40 | Distributed learning algorithm for feedforward neural networks | ||
| |||
| 14h41 | Watch, Ask, Learn, and Improve: a lifelong learning cycle for visual recognition | ||
| |||
| 14h42 | Memory management for data streams subject to concept drift | ||
| |||
| 14h43 | Towards incremental deep learning: multi-level change detection in a hierarchical visual recognition architecture | ||
| |||
| 14h44 | Classification | ||
| 14h44 | Boosting face recognition via neural Super-Resolution | ||
| |||
| 15h04 | Parallelized rotation and flipping INvariant Kohonen maps (PINK) on GPUs | ||
| |||
| 15h24 | Sparse Least Squares Support Vector Machines via Multiresponse Sparse Regression | ||
| |||
| 15h44 | anomaly detection on spectrograms using data-driven and fixed dictionary representations | ||
| |||
| 16h04 | Using semantic similarity for multi-label zero-shot classification of text documents | ||
| |||
| 16h24 | Active transfer learning for activity recognition | ||
| |||
| 16h44 | Classification Poster spotlights | ||
| 16h44 | Tuning the Distribution Dependent Prior in the PAC-Bayes Framework based on Empirical Data | ||
| |||
| 16h45 | Random Forests Model Selection | ||
| |||
| 16h46 | The WiSARD Classifier | ||
| |||
| 16h47 | Policy-gradient methods for Decision Trees | ||
| |||
| 16h48 | Multicriteria optimized MLP for imbalanced learning | ||
| |||
| 16h49 | Activity recognition with echo state networks using 3D body joints and objects category | ||
| |||
| 16h50 | From User-independent to Personal Human Activity Recognition Models Using Smartphone Sensors | ||
| |||
| 16h51 | One-class classification algorithm based on convex hull | ||
| |||
| 16h52 | Converting SVDD scores into probability estimates | ||
| |||
| 16h53 | Coffee break and poster exhibition | ||
Friday 29 April 2016
| 09h00 | Deep learning Organized by Alessandro Sperduti (Italy), Jose C. Principe (USA), Plamen Angelov (UK) | ||
| 09h00 | Challenges in Deep Learning | ||
| |||
| 09h20 | Deep Reservoir Computing: A Critical Analysis | ||
| |||
| 09h40 | Deep Learning Vector Quantization | ||
| |||
| 10h00 | Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks | ||
| |||
| 10h20 | Augmenting a convolutional neural network with local histograms - A case study in crop classification from high-resolution UAV imagery | ||
| |||
| 10h40 | Deep learning Poster spotlights | ||
| 10h40 | Stochastic gradient estimate variance in contrastive divergence and persistent contrastive divergence | ||
| |||
| 10h41 | An Experiment in Pre-Emphasizing Diversified Deep Neural Classifiers | ||
| |||
| 10h42 | Comparison of Four- and Six-Layered Configurations for Deep Network Pretraining | ||
| |||
| 10h43 | Learning Embeddings for Completion and Prediction of Relationnal Multivariate Time-Series | ||
| |||
| 10h44 | Spatial Chirp-Z Transformer Networks | ||
| |||
| 10h45 | Coffee break | ||
| 11h05 | Clustering and feature selection | ||
| 11h05 | Fast Support Vector Clustering | ||
| |||
| 11h25 | Fast in-memory spectral clustering using a fixed-size approach | ||
| |||
| 11h45 | Spectral clustering and discriminant analysis for unsupervised feature selection | ||
| |||
| 12h05 | Clustering and feature selection Poster spotlights | ||
| 12h05 | Clustering from two data sources using a kernel-based approach with weight coupling | ||
| |||
| 12h06 | Genetic Algorithm with Novel Crossover, Selection and Health Check for Clustering | ||
| |||
| 12h07 | PSCEG: an unbiased parallel subspace clustering algorithm using exact grids | ||
| |||
| 12h08 | Initialization of big data clustering using distributionally balanced folding | ||
| |||
| 12h09 | RBClust: High quality class-specific clustering using rule-based classification | ||
| |||
| 12h10 | K-means for Datasets with Missing Attributes: Building Soft Constraints with Observed and Imputed Values | ||
| |||
| 12h11 | Instance and feature weighted k-nearest-neighbors algorithm | ||
| |||
| 12h12 | Spatio-temporal feature selection for black-box weather forecasting | ||
| |||
| 12h13 | Parallelized unsupervised feature selection for large-scale network traffic analysis | ||
| |||
| 12h14 | Lunch | ||
| 13h45 | Information Visualisation and Machine Learning: Techniques, Validation and Integration Organized by Beno?t Fr?nay, Bruno Dumas (Belgium) | ||
| 13h45 | Information visualisation and machine learning: characteristics, convergence and perspective | ||
| |||
| 14h05 | Enhancing a social science model-building workflow with interactive visualisation | ||
| |||
| 14h25 | Informative data projections: a framework and two examples | ||
| |||
| 14h45 | Human-centered machine learning through interactive visualization: review and open challenges | ||
| |||
| 15h05 | Information Visualisation and Machine Learning: Techniques, Validation and Integration Poster spotlights | ||
| 15h05 | A state-space model on interactive dimensionality reduction | ||
| |||
| 15h06 | Visualizing stacked autoencoder language learning | ||
| |||
| 15h07 | Incremental hierarchical indexing and visualisation of large image collections | ||
| |||
| 15h08 | Robotics and reinforcement learning Poster spotlights | ||
| 15h08 | Learning contextual affordances with an associative neural architecture | ||
| |||
| 15h09 | Neural fitted actor-critic | ||
| |||
| 15h10 | Simultaneous estimation of rewards and dynamics from noisy expert demonstrations | ||
| |||
| 15h11 | On the improvement of static force capacity of humanoid robots based on plants behavior | ||
| |||
| 15h12 | Grounding the experience of a visual field through sensorimotor contingencies | ||
| |||
| 15h13 | Semantic Role Labelling for Robot Instructions using Echo State Networks | ||
| |||
| 15h14 | Human detection and classification of landing sites for search and rescue drones | ||
| |||
| 15h15 | Coffee break and poster exhibition | ||
| 16h45 | End of conference | ||