Since 1993, ESANN has become a reference for researchers on fundamental and theoretical aspects of artificial neural networks, computational intelligence, machine learning and related topics. Each year, around 120 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field.
The ESANN 2017 conference follows this tradition, while adapting its scope to the new developments in the field. The ESANN conferences cover artificial neural networks, machine learning, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered.
The twenty-fifth ESANN will be organised in Bruges, on 26-28 April 2017. It has become a tradition to hold the conference in this beautiful, human-size mediaeval city, whose atmosphere is favourable to efficient work but also to enjoyable cultural visits and relaxation. The centre of Bruges is a UNESCO World Heritage site.
Deep and kernel methods: best of two worlds Bridging deep and kernel methods
L. Belanche, M. Costa-jussa
Structure optimization for deep multimodal fusion networks using graph-induced kernels
D. Ramachandram, M. Lisicki, T. J. Shields, M. R. Amer, G. W. Taylor
Scalable Hybrid Deep Neural Kernel Networks
S. Mehrkanoon, A. Zell, J. A. K. Suykens
Learning dot-product polynomials for multiclass problems
I. Lauriola, M. Donini, F. Aiolli
Support vector components analysis
M. van der Ree, J. Roerdink, C. Phillips, G. Garraux, E. Salmon, M. Wiering
Algebraic multigrid support vector machines
E. Sadrfaridpour, S. Jeereddy, K. Kennedy, A. Luckow, T. Razzaghi, I. Safro
Attention-based Information Fusion using Multi-Encoder-Decoder Recurrent Neural Networks
S. Baier, S. Spieckermann, V. Tresp
Fusion of Stereo Vision for Pedestrian Recognition using Convolutional Neural Networks
D. O. Pop, A. Rogozan, F. Nashashibi, A. Bensrhair
Training convolutional networks with weight–wise adaptive learning rates
A. Mosca, G. Magoulas
Invariant representations of images for better learning
M. M. Issakkimuthu, S. K. V
Feature Extraction for On-Road Vehicle Detection Based on Support Vector Machine
S. G. Silva Filho, R. Freire, L. d. S. Coelho
Predicting Time Series with Space-Time Convolutional and Recurrent Neural Networks
W. Groß, S. Lange, J. Bödecker, M. Blum
Randomized Machine Learning approaches: analysis and developments
Randomized Machine Learning Approaches: Recent Developments and Challenges
C. Gallicchio, J. D. Martín-Guerrero, A. Micheli, E. Soria-Olivas
Fisher memory of linear Wigner echo state networks
P. Tino
Generalization Performances of Randomized Classifiers and Algorithms built on Data Dependent Distributions
L. Oneto, S. Ridella, D. Anguita
ELM Preference Learning for Physiological Data
D. Bacciu, M. Colombo, D. Morelli, D. Plans
Advanced query strategies for Active Learning with Extreme Learning Machines
A. Akusok, E. Eirola, Y. Miche, A. Gritsenko, A. Lendasse
Random projection initialization for deep neural networks
P. IW Wójcik, M. Kurdziel
Classification
Fine-grained event learning of human-object interaction with LSTM-CRF
T. Do, J. Pustejovsky
Distance metric learning: a two-phase approach
B. Nguyen, C. Morell, B. De Baets
An EM transfer learning algorithm with applications in bionic hand prostheses
B. Paassen, A. Schulz, J. Hahne, B. Hammer
Dropout Prediction at University of Genoa: a Privacy Preserving Data Driven Approach
L. Oneto, A. Siri, G. Luria, D. Anguita
Physical activity recognition from sub-bandage sensors using both feature selection and extraction
E. D'Andrea, F. Di Francesco, V. Dini, B. Lazzerini, M. Romanelli,
P. Salvo
A multi-criteria meta-learning method to select under-sampling algorithms for imbalanced datasets
R. Morais, P. Miranda, R. Silva
Large-scale nonlinear dimensionality reduction for network intrusion detection
Y. Hamid, L. Journaux, J. A. Lee, L. Sautot, N. Bushra, M. Sugumaran
Acceleration of Prototype Based Models with Cascade Computation
C. Karaoguz, A. Gepperth
Automatic crime report classi cation through a weightless neural network
R. Adnet Pinho, W. Brito, C. Motta, . Lima
Efficient Neural-based patent document segmentation with Term Order Probabilities
D. Silva de Carvalho, M.-L. Nguyen
Biomedical data analysis in translational research: integration of expert knowledge and interpretable models
Biomedical data analysis in translational research: integration of expert knowledge and interpretable models
G. Bhanot, M. Biehl, T. Villmann, D. Zühlke
Feature Relevance Bounds for Linear Classification
C. Göpfert, L. Pfannschmidt, B. Hammer
Prediction of preterm infant mortality with Gaussian process classification
O.-P. Rinta-Koski, S. Särkkä, J. Hollmén, M. Leskinen, S. Andersson
Comparison of strategies to learn from imbalanced classes for computer aided diagnosis of inborn steroidogenic disorders
S. Ghosh, E. S. Baranowski, R. van Veen, G.-J. de Vries, M. Biehl, W. Arlt,
P. Tino, K. Bunte
Environmental signal processing: new trends and applications
Environmental signal processing: new trends and applications
M. Puigt, G. Delmaire, G. Roussel
Solving Inverse Source Problems for Sources with Arbitrary Shapes using Sensor Networks
J. Murray-Bruce, P. L. Dragotti
Non-negative decomposition of geophysical dynamics
M. Lopez-Radcenco, A. Aïssa-El-Bey, P. Ailliot, R. Fablet
Impact of the initialisation of a blind unmixing method dealing with intra-class variability
C. Revel, Y. Deville, V. Achard, X. Briottet
Application of Tensor and Matrix Completion on Environmental Sensing Data
M. Giannopoulos, S. Savvaki, G. Tsagkatakis, P. Tsakalides
Indoor air pollutant sources using Blind Source Separation Methods
R. Ouaret, A. Ionescu, O. Ramalho, Y. Candau
High dimensionality voltammetric biosensor data processed with artificial neural networks
A. González-Calabuig, G. Faura, M. del Valle Kernels, graphs and clustering
Learning sparse models of diffusive graph signals
S. Dong, D. Thanou, P.-A. Absil, P. Frossard
The Conjunctive Disjunctive Node Kernel
D. Tran Van, A. Sperduti, F. Costa
POKer: a Partial Order Kernel for Comparing Strings with Alternative Substrings
M. Abdollahyan, F. Smeraldi
Accelerating stochastic kernel SOM
J. Mariette, F. Rossi, M. Olteanu, N. Villa-Vialaneix
Viral initialization for spectral clustering
V. Petrosyan, A. Proutiere
Approximated Neighbours MinHash Graph Node Kernel
N. Navarin, A. Sperduti
Fast hyperparameter selection for graph kernels via subsampling and multiple kernel learning
M. Donini, N. Navarin, I. Lauriola, F. Aiolli, F. Costa
A Simple Cluster Validation Index with Maximal Coverage
S. Jauhiainen, T. Karkkainen
The Top 10 Topics in Machine Learning Revisited: A Quantitative Meta-Study
P. Glauner, M. Du, V. Paraschiv, A. Boytsov, I. Lopez Andrade,
J. A. Meira, P. Valtchev, R. State
Regression, robots and biological systems
Piecewise-Bézier C1 smoothing on manifolds with application to wind field estimation
P.-Y. Gousenbourger, E. Massart, A. Musolas, P.-A. Absil, J. M. Hendrickx,
L. Jacques, Y. Marzouk
Reducing variance due to importance weighting in covariate shift bias correction
V.-T. Tran, A. Aussem
Complex activity patterns generated by short-term synaptic plasticity
B. Sandor, C. Gros
Criticality in Biocomputation
T. olde Scheper
Scholar Performance Prediction using Boosted Regression Trees Techniques
B. Stearns, F. Rangel, F. Rangel, F. Faria, J. Oliveira
Imitation learning for a continuum trunk robot
M. Malekzadeh Shafaroudi, J. F. Queißer, J. J. Steil
ELM vs. WiSARD: a performance comparison
L. Oliveira, F. França
A novel principle for causal inference in data with small error variance
P. Blöbaum, S. Shimizu, T. Washio
Learning null space projections fast
J. Manavalan, M. Howard
Comparison of adaptive MCMC methods
E. Milgo, N. Ronoh, P. W. Wagacha, B. Manderick
Pseudo-analytical solutions for stochastic options pricing using Monte Carlo
simulation and Breeding PSO-trained neural networks
S. Palmer, D. Gorse
Spikes as regularizers
A. Søgaard
Moving Least Squares Support Vector Machines for weather temperature prediction
Z. Karevan, Y. Feng, J. A. K. Suykens
A Robust Minimal Learning Machine based on the M-Estimator
J. Gomes, D. Mesquita, A. Freire, A. Souza Junior, T. Karkkainen
Processing, Mining and Visualizing Massive Urban Data
Processing, mining and visualizing massive urban data
P. Borgnat, E. Côme, L. Oukhellou
Anomaly detection and characterization in smart card logs using NMF and Tweets
E. Tonnelier, N. Baskiotis, V. Guigue, P. Gallinari
Using degree constrained gravity null-models to understand the structure of journeys' networks in bicycle sharing systems
R. Cazabet, P. Borgnat, P. Jensen
A neuro-symbolic approach to GPS trajectory classification
D. Carvalho, F. França, R. Barbosa, D. Cardoso
Non-negative matrix factorization as a pre-processing tool for travelers
temporal profiles clustering
L. Carel, P. Alquier
Extracting urban water usage habits from smart meter data: a functional clustering approach
N. Cheifetz, A. Same, Z. Sabir, A.-C. Sandraz, C. Féliers
Multiscale Spatio-Temporal Data Aggregation and Mapping for Urban Data Exploration
A. Remy, E. Côme
Detection of non-recurrent road traffic events based on clustering indicators
P.-A. Laharotte, R. Billot, N.-E. El Faouzi
Signal and image processing, collaborative filtering Collaborative filtering with neural networks
J. Feigl, M. Bogdan
Investigating optical transmission error correction using wavelet transforms
W. Binjumah, A. Redyuk, R. Adams, N. Davey, Y. Sun
WiSARDrp for Change Detection in Video Sequences
M. De Gregorio, G. Maurizio
Learning human behaviors and lifestyle by capturing temporal relations in mobility patterns
E. Ben Zion, B. Lerner
Hierarchical Combination of Video Features for Personalised Pain Level Recognition
P. Thiam, V. Kessler, F. Schwenker
A performance acceleration algorithm of spectral unmixing via subset selection
J. Ke, Y. Guo, A. Sowmya, T. Bednarz
Myoelectrical signal classification based on S transform and two-directional 2DPCA
H.-B. Xie, H. Liu
Hyper-spectral frequency selection for the classification of vegetation diseases
K. Dijkstra, J. van de Loosdrecht, L. Schomaker, M. Wiering
Outlining a simple and robust method for the automatic detection of EEG arousals
I. Fernández-Varela, D. Álvarez-Estévez, E. Hernández-Pereira,
V. Moret-Bonillo
A decision support system based on cellular automata to help the control of late blight in tomato cultures
G. Vianna, G. Oliveira, G. Cunha
Comparison of manual and semi-manual delineations for classifying glioblastoma multiforme patients based on histogram and texture MRI features
A. Ion-Margineanu, S. Van Cauter, D. M Sima, F. Maes, S. Sunaert,
U. Himmelreich, S. Van Huffel
Latent variable analysis in hospital electric power demand using non-negative matrix factorization
D. García, I. Díaz, D. Pérez, A. Cuadrado, M. Domínguez
Supporting generative models of spatial behavior by user interaction
R. Hug, W. Hübner, M. Arens
Algorithmic Challenges in Big Data Analytics
Algorithmic challenges in big data analytics
V. Bolón-Canedo, B. Remeseiro, K. Sechidis, D. Martínez-Rego,
A. Alonso-Betanzos
Partition-wise Recurrent Neural Networks for Point-based AIS Trajectory Classification
X. Jiang, E. N. de Souza, X. Liu, B. H. Soleimani, X. Wang, D. L. Silver,
S. Matwin
Scalable approximate k-NN Graph construction based on Locality Sensitive Hashing
C. Eiras-Franco, L. Kanthan, A. Alonso-Betanzos, D. Martínez-Rego
Degrees of Freedom in Regression Ensembles
R. Henry, G. Brown
Mutual information for improving the efficiency of the SCH algorithm
D. Fernandez-Francos, O. Fontenla-Romero, A. Alonso-Betanzos, G. Brown .
A distributed approach for classification using distance metrics
L. Morán-Fernández, V. Bolón-Canedo, A. Alonso-Betanzos
Deep learning
Local Lyapunov Exponents of Deep RNN
C. Gallicchio, A. Micheli, L. Silvestri
Learning Semantic Prediction using Pretrained Deep Feedforward Networks
J. Wagner, V. Fischer, M. Herman, S. Behnke
Deep convolutional neural networks for detecting noisy neighbours in cloud
infrastructure
B. Ordozgoiti, A. Mozo, S. Gómez Canaval, U. Margolin, E. Rosensweig,
I. Segall
Real-time convolutional networks for sonar image classification in low-power embedded systems
M. Valdenegro-Toro
Approximate operations in Convolutional Neural Networks with RNS data representation
V. Arrigoni, B. Rossi, P. Fragneto, G. Desoli
Learning convolutional neural network to maximize Pos@Top performancemeasure
Y. Geng, L. Ru-Ze, W. Li, J. Wang, L. Gaoyuan, X. Chenhao, W. Jing-Yan
Active learning strategy for CNN combining batchwise Dropout and
Query-By-Committee
M. Ducoffe, F. Precioso
A Deep Q-Learning Agent for L-Game with Variable Batch Training
P. Giannakopoulos, Y. Cotronis
TimeNet: Pre-trained deep recurrent neural network for time series
classification
P. Malhotra, V. TV, L. Vig, P. Agarwal, G. Shroff
Uncertain photometric redshifts via combining deep convolutional and mixture density networks
A. D'Isanto, K. L. Polsterer
Feature Extraction and Learning for RSSI based Indoor Device Localization
S. Timotheatos, G. Tsagkatakis, P. Tsakalides, P. Trahanias
Author index
Committees