Wednesday 24 April 2019
| 09h00 | Opening | ||
| 09h10 | Classification and Bayesian learning | ||
| 09h10 | Conditional BRUNO: a neural process for exchangeable labelled data | ||
| |||
| 09h30 | interpretable dynamics models for data-efficient reinforcement learning | ||
| |||
| 09h50 | PAC-Bayes and Fairness: Risk and Fairness Bounds on Distribution Dependent Fair Priors | ||
| |||
| 10h10 | DropConnect for Evaluation of Classification Stability in Learning Vector Quantization | ||
| |||
| 10h30 | Pixel-wise Conditioning of Generative Adversarial Networks | ||
| |||
| 10h50 | Committees as Artificial Organisms - Evolution and Adaptation | ||
| |||
| 11h10 | Classification and Bayesian learning Poster spotlights | ||
| 11h10 | Towards a device-free passive presence detection system with Bluetooth Low Energy beacons | ||
| |||
| 11h11 | Defending against poisoning attacks in online learning settings | ||
| |||
| 11h12 | Hybrid vibration signal monitoring approach for rolling element bearings | ||
| |||
| 11h13 | Modal sense classification with task-specific context embeddings | ||
| |||
| 11h14 | Adversarial robustness of linear models: regularization and dimensionality | ||
| |||
| 11h15 | A Simple and Effective Scheme for Data Pre-processing in Extreme Classification | ||
| |||
| 11h16 | MAP best performances prediction for endurance runners | ||
| |||
| 11h17 | TrIK-SVM : an alternative decomposition for kernel methods in Kreı̆n spaces | ||
| |||
| 11h18 | Coffee break | ||
| 11h35 | Embeddings and Representation Learning for Structured Data Organized by Benjamin Paaßen (Germany), Claudio Gallicchio, Alessio Micheli, Alessandro Sperduti (Italy) | ||
| 11h35 | Embeddings and Representation Learning for Structured Data | ||
| |||
| 11h55 | Graph generation by sequential edge prediction | ||
| |||
| 12h15 | On the definition of complex structured feature spaces | ||
| |||
| 12h35 | Embeddings and Representation Learning for Structured Data Poster spotloghts | ||
| 12h35 | Deep Weisfeiler-Lehman assignment kernels via multiple kernel learning | ||
| |||
| 12h36 | Predicting vehicle behaviour using LSTMs and a vector power representation for spatial positions | ||
| |||
| 12h37 | Efficient learning of email similarities for customer support | ||
| |||
| 12h38 | Nonnegative matrix factorization with polynomial signals via hierarchical alternating least squares | ||
| |||
| 12h39 | Lunch | ||
| 14h00 | Deep learning and CNN | ||
| 14h00 | Deep Embedded SOM: joint representation learning and self-organization | ||
| |||
| 14h20 | Deep convolutional neural network for survival estimation of Amyotrophic Lateral Sclerosis patients | ||
| |||
| 14h40 | Detecting adversarial examples with inductive Venn-ABERS predictors | ||
| |||
| 15h00 | Learning Rich Event Representations and Interactions for Temporal Relation Classification | ||
| |||
| 15h20 | L1-norm double backpropagation adversarial defense | ||
| |||
| 15h40 | Application of deep neural networks for automatic planning in radiation oncology treatments | ||
| |||
| 16h00 | Conditional WGAN for grasp generation | ||
| |||
| 16h20 | Deep learning and CNN Poster spotlights | ||
| 16h20 | Multilingual short text categorization using convolutional neural network | ||
| |||
| 16h21 | Fast and reliable architecture selection for convolutional neural networks | ||
| |||
| 16h22 | On the Speedup of Deep Reinforcement Learning Deep Q-Networks (RL-DQNs) | ||
| |||
| 16h23 | Deep Autoencoder Feature Extraction for Fault Detection of Elevator Systems | ||
| |||
| 16h24 | Detecting Ghostwriters in High Schools | ||
| |||
| 16h25 | Design of Power-Efficient FPGA Convolutional Cores with Approximate Log Multiplier | ||
| |||
| 16h26 | Improving Pedestrian Recognition using Incremental Cross Modality Deep Learning | ||
| |||
| 16h27 | Machine learning in research and development of new vaccines products: opportunities and challenges | ||
| |||
| 16h28 | Real-time Convolutional Neural Networks for emotion and gender classification | ||
| |||
| 16h30 | Coffee break and poster exhibition | ||
| 18h15 | Walking tour of Bruges with guides | ||
Thursday 25 April 2019
| 09h00 | Learning methods and optimization | ||
| 09h00 | Experimental study of the neuron-level mechanisms emerging from backpropagation | ||
| |||
| 09h20 | Learning multimodal fixed-point weights using gradient descent | ||
| |||
| 09h40 | Preconditioned conjugate gradient algorithms for graph regularized matrix completion | ||
| |||
| 10h00 | Direct calculation of out-of-sample predictions in multi-class kernel FDA | ||
| |||
| 10h20 | Complex Valued Gated Auto-encoder for Video Frame Prediction | ||
| |||
| 10h40 | Learning methods and optimization Poster spotlights | ||
| 10h41 | On overfitting of multilayer perceptrons for classification | ||
| |||
| 10h42 | Very Simple Classifier: a concept binary classifier to investigate features based on subsampling and locality | ||
| |||
| 10h43 | Sparse minimal learning machine using a diversity measure minimization | ||
| |||
| 10h44 | Minimax center to extract a common subspace from multiple datasets | ||
| |||
| 10h45 | Interpolation on the manifold of fixed-rank positive-semidefinite matrices for parametric model order reduction: preliminary results | ||
| |||
| 10h46 | Progress Towards Graph Optimization: Efficient Learning of Vector to Graph Space Mappings | ||
| |||
| 10h48 | Coffee break | ||
| 11h05 | 60 Years of Weightless Neural Systems Organized by Priscila M. V. Lima, Felipe M. G. França (Brazil), Massimo De Gregorio (Italy), Wilson R. de Oliveira (Brazil) | ||
| 11h05 | Systems with 'subjective feelings' - the perspective from weightless automata | ||
| |||
| 11h25 | Prediction of palm oil production with an enhanced n-Tuple Regression Network | ||
| |||
| 11h45 | Memory Efficient Weightless Neural Network using Bloom Filter | ||
| |||
| 12h05 | A WNN model based on Probabilistic Quantum Memories | ||
| |||
| 12h25 | 60 Years of Weightless Neural Systems Poster spotlights | ||
| 12h25 | Weightless neural systems for deforestation surveillance and image-based navigation of UAVs in the Amazon forest | ||
| |||
| 12h26 | An evolutionary approach for optimizing weightless neural networks | ||
| |||
| 12h27 | Modeling Sparse Data as Input for Weightless Neural Network | ||
| |||
| 12h29 | Lunch | ||
| 14h00 | Domain adaptation and learning | ||
| 14h00 | Multi-target feature selection through output space clustering | ||
| |||
| 14h20 | Feature relevance bounds for ordinal regression | ||
| |||
| 14h40 | User-steering interpretable visualization with probabilistic principal components analysis | ||
| |||
| 15h00 | Metric learning with submodular functions | ||
| |||
| 15h20 | Fusing Features based on Signal Properties and TimeNet for Time Series Classification | ||
| |||
| 15h40 | Domain adaptation and learning Poster spotlights | ||
| 15h40 | Metric learning with relational data | ||
| |||
| 15h41 | Feature and Algorithm Selection for Capacitated Vehicle Routing Problems | ||
| |||
| 15h42 | Topic-based historical information selection for personalized sentiment analysis | ||
| |||
| 15h43 | Bridging face and sound modalities through domain adaptation metric learning | ||
| |||
| 15h44 | Model selection for Extreme Minimal Learning Machine using sampling | ||
| |||
| 15h45 | Knowledge Discovery in Quarterly Financial Data of Stocks Based on the Prime Standard using a Hybrid of a Swarm with SOM | ||
| |||
| 15h46 | Dimensionality reduction in a hydraulic valve positioning application | ||
| |||
| 15h47 | Class-aware t-SNE: cat-SNE | ||
| |||
| 15h48 | Variational auto-encoders with Student’s t-prior | ||
| |||
| 15h49 | Streaming data analysis, concept drift and analysis of dynamic data sets Organized by Albert Bifet (France), Barbara Hammer, Frank-Michael Schleif (Germany) | ||
| 15h49 | Recent trends in streaming data analysis, concept drift and analysis of dynamic data sets | ||
| |||
| 16h09 | Online Bayesian Shrinkage Regression | ||
| |||
| 16h29 | Streaming data analysis, concept drift and analysis of dynamic data sets Poster spotlights | ||
| 16h29 | Reactive Soft Prototype Computing for frequent reoccurring Concept Drift | ||
| |||
| 16h30 | Beta Distribution Drift Detection for Adaptive Classifiers | ||
| |||
| 16h31 | Importance of user inputs while using incremental learning to personalize human activity recognition models | ||
| |||
| 16h32 | Coffee break and poster exhibition | ||
| 18h45 | VIsit of the "Halve maan" brewery | ||
| 19h30 | Conference dinner at the "Halve Maan" brewery | ||
Friday 26 April 2019
| 09h00 | Societal Issues in Machine Learning: When Learning from Data is Not Enough Organized by D. Bacciu (Italy), B. Biggio (Italy), P. J. G. Lisboa, (U.K.), J. D. Martín (Spain), L. Oneto (Italy), A. Vellido (Spain) | ||
| 09h00 | Societal Issues in Machine Learning: When Learning from Data is Not Enough | ||
| |||
| 09h20 | Privacy Preserving Synthetic Health Data | ||
| |||
| 09h40 | Fairness and Accountability of Machine Learning Models in Railway Market: are Applicable Railway Laws Up to Regulate Them? | ||
| |||
| 10h00 | Dynamic fairness - Breaking vicious cycles in automatic decision making | ||
| |||
| 10h20 | Detecting Black-box Adversarial Examples through Nonlinear Dimensionality Reduction | ||
| |||
| 10h40 | Societal Issues in Machine Learning: When Learning from Data is Not Enough Poster spotlights | ||
| 10h40 | Deep RL for autonomous robots: limitations and safety challenges | ||
| |||
| 10h41 | Explaining classification systems using sparse dictionaries | ||
| |||
| 10h42 | Coffee break | ||
| 11h00 | Statistical physics of learning and inference Organized by Michael Biehl (The Netherlands), Nestor Caticha (Brazil), Manfred Opper, Thomas Villmann (Germany) | ||
| 11h00 | Statistical physics of learning and inference | ||
| |||
| 11h20 | Trust, law and ideology in a NN agent model of the US Appellate Courts | ||
| |||
| 11h40 | On-line learning dynamics of ReLU neural networks using statistical physics techniques | ||
| |||
| 12h00 | Statistical physics of learning and inference Poster spotlights | ||
| 12h00 | Noise helps optimization escape from saddle points in the neural dynamics | ||
| |||
| 12h01 | Image processing and transfer learning Poster spotlights | ||
| 12h01 | Deep hybrid approach for 3D plane segmentation | ||
| |||
| 12h02 | visualizing image classification in fourier domain | ||
| |||
| 12h03 | Blind-spot network for image anomaly detection: A new approach to diabetic retinopathy screening | ||
| |||
| 12h04 | A document detection technique using convolutional neural networks for optical character recognition systems | ||
| |||
| 12h05 | Learning super-resolution 3D segmentation of plant root MRI images from few examples | ||
| |||
| 12h06 | Analyzing spatial dissimilarities in high-resolution geo-data : a case study of four European cities | ||
| |||
| 12h07 | Computerized tool for identification and enhanced visualization of Macular Edema regions using OCT scans | ||
| |||
| 12h08 | A best-first branch-and-bound search for solving the transductive inference problem using support vector machines | ||
| |||
| 12h09 | LEAP nets for power grid perturbations | ||
| |||
| 12h10 | Active one-shot learning with Prototypical Networks | ||
| |||
| 12h11 | Transfer Learning for transferring machine-learning based models among hyperspectral sensors | ||
| |||
| 12h12 | Lunch | ||
| 13h40 | Time series and signal processing | ||
| 13h40 | Multiple-Kernel dictionary learning for reconstruction and clustering of unseen multivariate time-series | ||
| |||
| 14h00 | Tensor factorization to extract patterns in multimodal EEG data | ||
| |||
| 14h20 | Beyond Pham's algorithm for joint diagonalization | ||
| |||
| 14h40 | Frequency Domain Transformer Networks for Video Prediction | ||
| |||
| 15h00 | Time series and signal processing Poster spotlights | ||
| 15h00 | Comparison between DeepESNs and gated RNNs on multivariate time-series prediction | ||
| |||
| 15h01 | Autoregressive Convolutional Recurrent Neural Network for Univariate and Multivariate Time Series Prediction | ||
| |||
| 15h02 | Using Deep Learning and Evolutionary Algorithms for Time Series Forecasting | ||
| |||
| 15h03 | lightweight autonomous bayesian optimization of Echo-State Networks | ||
| |||
| 15h04 | time series modelling of market price in real-time bidding | ||
| |||
| 15h05 | Dynamical systems and reinforcement learning Poster spotlights | ||
| 15h05 | Short-term trajectory planning using reinforcement learning within a neuromorphic control architecture | ||
| |||
| 15h06 | training networks separately on static and dynamic obstacles improves collision avoidance during indoor robot navigation | ||
| |||
| 15h07 | Human feedback in continuous actor-critic reinforcement learning | ||
| |||
| 15h08 | Chasing the Echo State Property | ||
| |||
| 15h09 | Coffee break and poster exhibition | ||
| 17h00 | End of conference | ||