Communities
Select a community to browse its collections.
NR vitenarkiv [373]
Recently Added
-
MAP IT to Visualize Representations
(Journal article, 2024)MAP IT visualizes representations by taking a fundamentally different approach to dimensionality reduction. MAP IT aligns distributions over discrete marginal probabilities in the input space versus the target space, thus ... -
Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks
(Journal article; Peer reviewed, 2024)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 ... -
Tilgjengelige informasjonskapsler
(NR-rapport;, Research report, 2025)Prosjektet «Tilgjengelige informasjonskapsler» undersøker universell utforming av cookie-bannere og brukernes oppfatning av disse, med fokus på personer med funksjonsnedsettelser. Vi har gjennomført en litteraturstudie, ... -
DIB-X: Formulating Explainability Principles for a Self-Explainable Model Through Information Theoretic Learning
(Peer reviewed; Journal article, 2024)The recent development of self-explainable deep learning approaches has focused on integrating well-defined explainability principles into learning process, with the goal of achieving these principles through optimization. ... -
Diffusion Models with Cross-Modal Data for Super-Resolution of Sentinel-2 To 2.5 Meter Resolution
(Peer reviewed; Journal article, 2024)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 ...
RSS 2.0