Institution
Norwegian Computing Center
Nonprofit•Oslo, Norway•
About: Norwegian Computing Center is a nonprofit organization based out in Oslo, Norway. It is known for research contribution in the topics: Bayesian probability & Deep learning. The organization has 306 authors who have published 782 publications receiving 29243 citations. The organization is also known as: Norsk Regnesentral.
Topics: Bayesian probability, Deep learning, Markov chain Monte Carlo, Security information and event management, Context (language use)
Papers published on a yearly basis
Papers
More filters
TL;DR: Principal Component Analysis is a multivariate exploratory analysis method useful to separate systematic variation from noise and to define a space of reduced dimensions that preserve noise.
8,660 citations
Vilnius University1, University of Ferrara2, Aarhus University3, University of Oslo4, Royal Institute of Technology5, Electromagnetic Geoservices6, University of Trieste7, Norwegian Computing Center8, University of Southern Denmark9, University of Santiago de Compostela10, Danske Bank11, Ruhr University Bochum12, Norwegian Meteorological Institute13, Norwegian Defence Research Establishment14, University of Auckland15, Norwegian University of Science and Technology16, Information Technology University17, Technical University of Ostrava18, Linköping University19, Karlsruhe Institute of Technology20, ETH Zurich21, Australian National University22, University of Modena and Reggio Emilia23, Cisco Systems, Inc.24, University of Buenos Aires25, University of Copenhagen26, University of Erlangen-Nuremberg27, Kazimierz Wielki University in Bydgoszcz28, National Scientific and Technical Research Council29, University of Valencia30, Paul Sabatier University31, University of Melbourne32, University of Nottingham33, University of Bristol34, CLC bio35, Princeton University36, La Trobe University37, Clemson University38
TL;DR: Dalton is a powerful general‐purpose program system for the study of molecular electronic structure at the Hartree–Fock, Kohn–Sham, multiconfigurational self‐consistent‐field, Møller–Plesset, configuration‐interaction, and coupled‐cluster levels of theory.
Abstract: Dalton is a powerful general-purpose program system for the study of molecular electronic structure at the Hartree-Fock, Kohn-Sham, multiconfigurational self-consistent-field, MOller-Plesset, confi ...
1,212 citations
TL;DR: This paper is an introduction to SIMULA, a programming language designed to provide a systems analyst with unified concepts which facilitate the concise description of discrete event systems.
Abstract: This paper is an introduction to SIMULA, a programming language designed to provide a systems analyst with unified concepts which facilitate the concise description of discrete event systems. A system description also serves as a source language simulation program. SIMULA is an extension of ALGOL 60 in which the most important new concept is that of quasi-parallel processing.
875 citations
01 Jun 2016
TL;DR: This paper proposes a novel approach to achieve high overall accuracy, while still achieving good accuracy for small objects in remote sensing images, and demonstrates the ideas on different deep architectures including patch-based and so-called pixel-to-pixel approaches, as well as their combination.
Abstract: We propose a deep Convolutional Neural Network (CNN) for land cover mapping in remote sensing images, with a focus on urban areas. In remote sensing, class imbalance represents often a problem for tasks like land cover mapping, as small objects get less prioritised in an effort to achieve the best overall accuracy. We propose a novel approach to achieve high overall accuracy, while still achieving good accuracy for small objects. Quantifying the uncertainty on a pixel scale is another challenge in remote sensing, especially when using CNNs. In this paper we use recent advances in measuring uncertainty for CNNs and evaluate their quality both qualitatively and quantitatively in a remote sensing context. We demonstrate our ideas on different deep architectures including patch-based and so-called pixel-to-pixel approaches, as well as their combination, by classifying each pixel in a set of aerial images covering Vaihingen, Germany. The results show that we obtain an overall classification accuracy of 87%. The corresponding F1- score for the small object class "car" is 80.6%, which is higher than state-of-the art for this dataset.
496 citations
TL;DR: The principal aim of this paper is to uncover the socio-technical complexity of establishing an information infrastructure, a complexity which so far has been severely underestimated by those involved.
434 citations
Authors
Showing all 310 results
| Name | H-index | Papers | Citations |
|---|---|---|---|
| Donald E. Knuth | 85 | 280 | 62076 |
| Paul Geladi | 52 | 223 | 24355 |
| Håvard Rue | 51 | 195 | 16220 |
| Harald Martens | 49 | 146 | 11179 |
| Peter Guttorp | 46 | 178 | 8768 |
| Arvid Lundervold | 42 | 151 | 6927 |
| Fred Espen Benth | 41 | 272 | 6108 |
| Ole Christian Lingjærde | 39 | 112 | 6953 |
| Tore Haug | 39 | 168 | 4338 |
| Kim H. Esbensen | 39 | 216 | 12851 |
| Arnoldo Frigessi | 38 | 137 | 6081 |
| Solveig Hofvind | 37 | 171 | 4990 |
| Dag Tjøstheim | 35 | 139 | 4740 |
| Ørnulf Borgan | 32 | 114 | 3835 |
| Ole Hanseth | 32 | 84 | 6109 |