Unsupervised representation learning has become an important ingredient of today’s deep learning systems. However, only a few methods exist that explain a learned vector embedding in the sense of providing information about which parts of an input are the most important for its representation. These methods generate the explanation for a given input after the model has been evaluated and tend to ...

Developing new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus. Recently, machine learning (ML)-based classifiers using functional connectivity (FC) for psychiatric disorders and healthy controls (HCs) are developed to identify brain markers. However, existing ML-based diagnostic models are prone to ...

The development of electricity storage solutions is crucial to support the integration of variable renewable electricity sources in electricity systems. This study experimentally characterizes a state-of-the-art full-scale electrical thermal energy storage (ETES) system in outdoor conditions. The system integrates a 600 kWh_th high-temperature latent heat storage module and a 13 kW_e ...

Background - The pursuit of automated methods to assess the extent of resection (EOR) in glioblastomas is challenging, requiring precise measurement of residual tumor volume. Many algorithms focus on preoperative scans, making them unsuitable for postoperative studies. Our objective was to develop a deep learning-based model for postoperative segmentation using magnetic resonance imaging (MRI). We ...

Diffusion models have obtained photo-realistic results on various super-resolution tasks. However, existing approaches typically require the availability of high-resolution and paired training data, which often is not readily available in many remote sensing scenarios. To enhance multi-spectral Sentinel 2 (S2) satellite images – at a ground sampling distance (GSD) ranging from 10m to 60m – without ...

Most integrated evanescent-field photonic sensors measure changes in either the real part or the imaginary part of the complex refractive index of the sample, i.e., refraction or absorption. Here we propose and experimentally demonstrate a near-infrared sensor based on a silicon nitride Mach-Zehnder interferometer which provides a direct measurement of the complex refractive index. Our architecture ...

The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading to unreliable predictions. Diagnosing and debiasing datasets is thus a necessity to ensure reliable model performance. In this paper, we present ConBias, a novel ...

There is an ongoing debate on the relationship between accelerated warming in the Arctic and extreme weather patterns in mid-latitudes. As extreme weather events have dramatic socioeconomic costs, it is important to investigate the possibility of the increased risk of such events in mid-latitudes. We investigated changes in the frequency of extreme weather events in Eastern Europe and Western to ...

Siden andre verdenskrig har det pågått et storstilt internasjonalt forskningsprosjekt med mål om å bruke fusjonsprosesser til å lage ren elektrisk energi for menneskeheten fra tilnærmet ubegrensede ressurser. Det pågår nå et storstilt kappløp for å utvikle den første demonstrasjonsreaktoren. Denne artikkelen gir en kortfattet beskrivelse av historien bak og status for kappløpet, og den avsluttes med ...

Long-range correlations manifested as power spectral density scaling 1/<i>f^β</i> for frequency f and a range of exponents <i>β</i> are investigated for a superposition of uncorrelated pulses with distributed durations τ. Closed-form expressions for the frequency power spectral density are derived for a one-sided exponential pulse function and several variants of bounded and unbounded ...