Wednesday 25 April 2018
| 09h00 | Opening | ||
| 09h10 | Deep learning and image processing | ||
| 09h10 | A Sub-Layered Hierarchical Pyramidal Neural Architecture for Facial Expression Recognition | ||
|
|||
| 09h30 | interpretation of convolutional neural networks for speech regression from electrocorticography | ||
|
|||
| 09h50 | transferring style in motion capture sequences with adversarial learning | ||
|
|||
| 10h10 | Properties of adv−1 � Adversarials of Adversarials | ||
|
|||
| 10h30 | Deep learning and image processing Poster spotlights |
||
| 10h30 | An analysis of subtask-dependency in robot command interpretation with dilated CNNs | ||
|
|||
| 10h31 | Image retrieval and ranking through Deep Comparative Neural Networks | ||
|
|||
| 10h32 | Incremental learning with deep neural networks using a test-time oracle | ||
|
|||
| 10h33 | Image-to-Text Transduction with Spatial Self-Attention | ||
|
|||
| 10h34 | Hierarchical Recurrent Filtering for Fully Convolutional DenseNets | ||
|
|||
| 10h35 | Towards cognitive automotive environment modelling: reasoning based on vector representations | ||
|
|||
| 10h36 | Inferencing based on unsupervised learning of disentangled representations | ||
|
|||
| 10h37 | Dynamic autonomous image segmentation based on Grow Cut | ||
|
|||
| 10h38 | Continuous convolutional object tracking | ||
|
|||
| 10h39 | Active Learning based on Transfer Learning Techniques for Image Classification | ||
|
|||
| 10h40 | Near-optimal facial emotion classification using a WiSARD-based weightless system | ||
|
|||
| 10h41 | Spatial pooling as feature selection method for object recognition | ||
|
|||
| 10h42 | Coffee break | ||
| 11h05 | Interaction and User Integration in Machine Learning for Information Visualisation Organized by Bruno Dumas, Benoit Fr�nay (Universit� de Namur), John Lee (Universit� catholique de Louvain, Belgium) |
||
| 11h05 | Information visualisation and machine learning: latest trends towards convergence | ||
|
|||
| 11h25 | VisCoDeR: A tool for visually comparing dimensionality reduction algorithms | ||
|
|||
| 11h45 | G-Rap: interactive text synthesis using recurrent neural network suggestions | ||
|
|||
| 12h05 | Interactive dimensionality reduction of large datasets using interpolation | ||
|
|||
| 12h25 | Nonlinear dimensionality reduction | ||
| 12h25 | Perplexity-free t-SNE and twice Student tt-SNE | ||
|
|||
| 12h45 | Nonlinear dimensionality reduction Poster spotlights |
||
| 12h45 | Generative Kernel PCA | ||
|
|||
| 12h46 | Extensive assessment of Barnes-Hut t-SNE | ||
|
|||
| 12h47 | Understanding wafer patterns in semiconductor production with variational auto-encoders | ||
|
|||
| 12h48 | Lunch | ||
| 14h15 | Classification | ||
| 14h15 | Feature noise tuning for resource efficient Bayesian Network Classifiers | ||
|
|||
| 14h35 | Reliable Patient Classification in Case of Uncertain Class Labels Using a Cross-Entropy Approach | ||
|
|||
| 14h55 | behaviour-based working memory capacity classification using recurrent neural networks | ||
|
|||
| 15h15 | Structuring and Solving Multi-Criteria Decision Making Problems using Artificial Neural Networks: a smartphone recommendation case | ||
|
|||
| 15h35 | Efficient accuracy estimation for instance-based incremental active learning | ||
|
|||
| 15h55 | Boolean kernels for interpretable kernel machines | ||
|
|||
| 16h15 | The minimum effort maximum output principle applied to Multiple Kernel Learning | ||
|
|||
| 16h35 | Classification Poster spotlights |
||
| 16h35 | One-class Autoencoder approach to classify Raman spectra outliers | ||
|
|||
| 16h36 | Radar Based Pedestrian Detection using Support Vector Machine and the Micro Doppler Effect | ||
|
|||
| 16h37 | Opposite neighborhood: a new method to select reference points of minimal learning machines | ||
|
|||
| 16h38 | A neural network cost function for highly class-imbalanced data sets | ||
|
|||
| 16h39 | Self-learning assembly systems during ramp-up | ||
|
|||
| 16h40 | Feasibility based Large Margin Nearest Neighbor metric learning | ||
|
|||
| 16h41 | Combining latent tree modeling with a random forest-based approach, for genetic association studies | ||
|
|||
| 16h42 | Graph based neural networks for automatic classification of multiple sclerosis clinical courses | ||
|
|||
| 16h43 | Coffee break and poster exhibition | ||
Thursday 26 April 2018
| 09h00 | Regression and recommendation systems | ||
| 09h00 | Extreme Minimal Learning Machine | ||
|
|||
| 09h20 | Learning with a Fisher surrogate loss in a small data regime | ||
|
|||
| 09h40 | Fast Power system security analysis with Guided Dropout | ||
|
|||
| 10h00 | Neural Networks for Implicit Feedback Datasets | ||
|
|||
| 10h20 | Regularize and explicit collaborative filtering with textual attention | ||
|
|||
| 10h40 | Regression and recommendation systems Poster spotlights |
||
| 10h40 | Adaptive random forests for data stream regression | ||
|
|||
| 10h41 | Cache-efficient Gradient Descent Algorithm | ||
|
|||
| 10h42 | Sensitivity analysis for predictive uncertainty | ||
|
|||
| 10h43 | Revisiting FISTA for Lasso: Acceleration Strategies Over The Regularization Path | ||
|
|||
| 10h44 | Coffee break | ||
| 11h05 | Shallow and Deep models for transfer learning and domain adaptation Organized by Siamak Mehrkanoon, Matthew Blaschko, Johan Suykens (KU Leuven, Belgium) |
||
| 11h05 | Shallow and Deep Models for Domain Adaptation problems | ||
|
|||
| 11h25 | Shallow and Deep models for transfer learning and domain adaptation Poster spotlights |
||
| 11h25 | Unsupervised domain adaptation of deep object detectors | ||
|
|||
| 11h26 | Machine Learning and Data Analysis in Astroinformatics Organized by Michael Biehl, Kerstin Bunte (University of Groningen, The Netherlands), Giuseppe Longo (University of Naples, Italy), Peter Tino (University of Birmingham, United Kingdom) |
||
| 11h26 | Machine learning and data analysis in astroinformatics | ||
|
|||
| 11h46 | Anomaly detection in star light curves using hierarchical Gaussian processes | ||
|
|||
| 12h06 | Latent representations of transient candidates from an astronomical image difference pipeline using Variational Autoencoders | ||
|
|||
| 12h26 | Machine Learning and Data Analysis in Astroinformatics Poster spotlights |
||
| 12h26 | Globular Cluster Detection in the Gaia Survey | ||
|
|||
| 12h27 | stellar formation rates in galaxies using machine learning models | ||
|
|||
| 12h28 | Prototype-based analysis of GAMA galaxy catalogue data | ||
|
|||
| 12h29 | Lunch | ||
| 14h00 | Deep Learning in Bioinformatics and Medicine Organized by M. Atencia (U. M�laga, Spain), D. Bacciu (U. Pisa, Italy), P. J. G. Lisboa (Liverpool John Moores U., UK), J. D. Martin, (U. Val�ncia, Spain), R. Stoean (Uni. Craiova, Romania), A. Vellido |
||
| 14h00 | Bioinformatics and medicine in the era of deep learning | ||
|
|||
| 14h20 | Controlling biological neural networks with deep reinforcement learning | ||
|
|||
| 14h40 | Learning compressed representations of blood samples time series with missing data | ||
|
|||
| 15h00 | Sleep staging with deep learning: a convolutional model | ||
|
|||
| 15h20 | Interpreting deep learning models for ordinal problems | ||
|
|||
| 15h40 | Deep Learning in Bioinformatics and Medicine Poster spotlights |
||
| 15h40 | Non-negative Matrix Factorization for Medical Imaging | ||
|
|||
| 15h41 | Multi-omics data integration using cross-modal neural networks | ||
|
|||
| 15h42 | DEEP: decomposition feature enhancement procedure for graphs | ||
|
|||
| 15h43 | Deep Echo State Networks for Diagnosis of Parkinson's Disease | ||
|
|||
| 15h44 | Capturing variabilities from Computed Tomography images with Generative Adversarial Networks (GANs) | ||
|
|||
| 15h45 | Pollen grain recognition using convolutional neural network | ||
|
|||
| 15h46 | Randomized Neural Networks Organized by Claudio Gallicchio, Alessio Micheli (University of Pisa, Italy), Peter Tino (University of Birmingham, United Kingdom) |
||
| 15h46 | Randomized Recurrent Neural Networks | ||
|
|||
| 16h06 | Bidirectional deep-readout echo state networks | ||
|
|||
| 16h26 | Forecasting Business Failure in Highly Imbalanced Distribution based on Delay Line Reservoir | ||
|
|||
| 16h46 | Randomized Neural Networks Poster spotlights |
||
| 16h46 | Estimation of the Human Concentration using Echo State Networks | ||
|
|||
| 16h47 | Quantifying the Reservoir Quality using Dimensionality Reduction Techniques | ||
|
|||
| 16h48 | Clustering and feature selection Poster spotlights |
||
| 16h48 | Scalable robust clustering method for large and sparse data | ||
|
|||
| 16h49 | clustering with decision trees: divisive and agglomerative approach | ||
|
|||
| 16h50 | Comparison of cluster validation indices with missing data | ||
|
|||
| 16h51 | Efficient approximate representations for computationally expensive features | ||
|
|||
| 16h52 | Regularised maximum-likelihood inference of mixture of experts for regression and clustering | ||
|
|||
| 16h53 | Feature selection for label ranking | ||
|
|||
| 16h54 | A novel filter algorithm for unsupervised feature selection based on a space filling measure | ||
|
|||
| 16h55 | Coffee break and poster exhibition | ||
Friday 27 April 2018
| 09h00 | Mathematical aspects of learning, and reinforcement learning | ||
| 09h00 | Asymptotic statistics for multilayer perceptron with ReLu hidden units | ||
|
|||
| 09h20 | Local Rademacher Complexity Machine | ||
|
|||
| 09h40 | A sharper bound on the Rademacher complexity of margin multi-category classifiers | ||
|
|||
| 10h00 | Slowness-based neural visuomotor control with an Intrinsically motivated Continuous Actor-Critic | ||
|
|||
| 10h20 | Mathematical aspects of learning, and reinforcement learning Poster spotlights |
||
| 10h20 | A variable projection method for block term decomposition of higher-order tensors | ||
|
|||
| 10h21 | Reinforcement Learning for High-Frequency Market Making | ||
|
|||
| 10h22 | Coffee break | ||
| 10h45 | Emerging trends in machine learning: beyond conventional methods and data Organized by Luca Oneto (University of Genoa), Nicol� Navarin (Univ. of Padua), Michele Donini (Istituto Italiano di Tecnologia), Davide Anguita (Univ. of Genoa, Italy) |
||
| 10h45 | Emerging trends in machine learning: beyond conventional methods and data | ||
|
|||
| 11h05 | Finding the most interpretable MDS rotation for sparse linear models based on external features | ||
|
|||
| 11h25 | Mixture of Hidden Markov Model as Tree Encoder | ||
|
|||
| 11h45 | Set point thresholds from topological data analysis and an outlier detector | ||
|
|||
| 12h05 | Emerging trends in machine learning: beyond conventional methods and data Poster spotlights |
||
| 12h05 | Differential private relevance learning | ||
|
|||
| 12h06 | On aggregation in ranking median regression | ||
|
|||
| 12h07 | Temporal transfer learning for drift adaptation | ||
|
|||
| 12h08 | LANN-DSVD: A privacy-preserving distributed algorithm for machine learning | ||
|
|||
| 12h09 | Vector Field Based Neural Networks | ||
|
|||
| 12h10 | Lunch | ||
| 13h40 | Temporal data, sequences and incremental learning | ||
| 13h40 | Non-Negative Tensor Dictionary Learning | ||
|
|||
| 14h00 | An extension of nonstationary fuzzy sets to heteroskedastic fuzzy time series | ||
|
|||
| 14h20 | Temporal data, sequences and incremental learning Poster spotlights |
||
| 14h20 | Surprisal-based activation in recurrent neural networks | ||
|
|||
| 14h21 | K-spectral centroid: extension and optimizations | ||
|
|||
| 14h22 | Temporal modeling of ALS using longitudinal data and long-short term memory-based algorithm | ||
|
|||
| 14h23 | Person Identification and Discovery With Wrist Worn Accelerometer Data | ||
|
|||
| 14h24 | CDTW-based classification for Parkinson's Disease diagnosis | ||
|
|||
| 14h25 | Personalizing human activity recognition models using incremental learning | ||
|
|||
| 14h26 | Short-term Memory of Deep RNN | ||
|
|||
| 14h27 | Effect of context in swipe gesture-based continuous authentication on smartphones | ||
|
|||
| 14h28 | Impact of Biases in Big Data Organized by Patrick Glauner (University of Luxembourg), Petko Valtchev (University of Quebec at Montreal, Canada), Radu State (University of Luxembourg) |
||
| 14h28 | Impact of Biases in Big Data | ||
|
|||
| 14h48 | Analysis of imputation bias for feature selection with missing data | ||
|
|||
| 15h08 | Impact of Biases in Big Data Poster spotlights |
||
| 15h08 | Systematics aware learning : a case study in high energy physics | ||
|
|||
| 15h09 | Optimization and metaheuristics Poster spotlights |
||
| 15h09 | Evolutionary RL for Container Loading | ||
|
|||
| 15h10 | Enhancement of a stochastic Markov-blanket framework with ant colony optimization, to uncover epistasis in genetic association studies | ||
|
|||
| 15h11 | Meerkats-inspired Algorithm for Global Optimization Problems | ||
|
|||
| 15h12 | Cheetah Based Optimization Algorithm: A Novel Swarm Intelligence Paradigm | ||
|
|||
| 15h13 | Evolutionary Composition of Customized Fault Localization Heuristics | ||
|
|||
| 15h14 | Order Crossover for the Inventory Routing Problem | ||
|
|||
| 15h16 | Coffee break and poster exhibition | ||
| 17h00 | End of conference | ||