In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics. The proposed network is composed by several recurrent groups of neurons that are trained to separately adapt to each timescale, in order to improve the system identification process. We test our framework on time series prediction tasks ...

We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent low dimensionality of the solution manifold to obtain approximation rates which are significantly superior to those provided by classical neural network approximation results. ...

Coupling between the ionized and neutral atmosphere through particle collisions allows an indirect study of the neutral atmosphere through measurements of ionospheric plasma parameters. We estimate the neutral density of the upper thermosphere above ~250 km with the European Incoherent Scatter Svalbard Radar (ESR) using the year-long operations of the International Polar Year from March 2007 to ...

Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the comprehensibility and traceability of the underlying decision-making strategies. As a remedy, numerous post-hoc and self-explanation methods have been developed to interpret the models’ behavior. Those methods, in addition, ...

The Einstein Cross, Q 2237+0305, has been photometrically observed in four bands on two successive nights at NOT (La Palma, Spain) in October 1995. Three independent algorithms have been used to analyse the data: an automatic image decomposition technique, a CLEAN algorithm and the new MCS deconvolution code. The photometric and astrometric results obtained with the three methods are presented. ...

The time series cluster kernel (TCK) provides a powerful tool for analysing multivariate time series subject to missing data. TCK is designed using an ensemble learning approach in which Bayesian mixture models form the base models. Because of the Bayesian approach, TCK can naturally deal with missing values without resorting to imputation and the ensemble strategy ensures robustness to hyperparameters, ...

We tackle the problem of classifying Electrocardiography (ECG) signals with the aim of predicting the onset of Paroxysmal Atrial Fibrillation (PAF). Atrial fibrillation is the most common type of arrhythmia, but in many cases PAF episodes are asymptomatic. Therefore, in order to help diagnosing PAF, it is important to design procedures for detecting and, more importantly, predicting PAF episodes. ...

Increased human presence and commercial activities in the Barents Sea (fishing, offshore oil and gas exploration) are amplifying the need for large-scale operational ocean monitoring of the eventual oil spills in the region. The geographical location and climate impose additional constraints on satellite-based monitoring, making it necessary to use Synthetic Aperture Radar (SAR). Dark features or ...

The data-driven nature of deep learning (DL) models for semantic segmentation requires a large number of pixel-level annotations. However, large-scale and fully labeled medical datasets are often unavailable for practical tasks. Recently, partially supervised methods have been proposed to utilize images with incomplete labels in the medical domain. To bridge the methodological gaps in ...

In this paper, we introduce a new framework to train a class of recurrent neural network, called Echo State Network, to predict real valued time-series and to provide a visualization of the modeled system dynamics. The method consists in projecting the output of the internal layer of the network on a lower dimensional space, before training the output layer to learn the target task. Notably, we ...