Browsing NTNU Open by Author "Gundersen, Odd Erik"
Now showing items 21-40 of 55
-
Enhancing the Situation Awareness of Decision Makers by Applying Case-Based Reasoning on Streaming Data
Gundersen, Odd Erik (Doctoral thesis at NTNU;2014:315, Doctoral thesis, 2014)Data is generally expected to continue its exponential growth the next five to ten years. However, it is commonly agreed that the amount of data that currently exist is abundant and that there is still much to achieve ... -
Evaluation of Multi-step Forecasting Models: An Empirical Deep Learning Study
Strøm, Eivind (Master thesis, 2021)Denne masteroppgaven omhandler evaluering av metoder for flerperiodeprediksjon av tidsserier ved å gjennomføre en empirisk studie med dype læringsmodeller. I dag blir modeller for flerperiodeprediksjon evaluert ved at en ... -
Explaining Traffic Situations – Architecture of a Virtual Driving Instructor
Sandberg, Martin K. Hoel; Rehm, Johannes; Mnoucek, Matej; Gundersen, Odd Erik; Reshodko, Irina (Peer reviewed; Journal article, 2020)Intelligent tutoring systems become more and more common in assisting human learners. Distinct advantages of intelligent tutoring systems are personalized teaching tailored to each student, on-demand availability not ... -
The fundamental principles of reproducibility
Gundersen, Odd Erik (Peer reviewed; Journal article, 2021)Reproducibility is a confused terminology. In this paper, I take a fundamental view on reproducibility rooted in the scientific method. The scientific method is analysed and characterized in order to develop the terminology ... -
Implementing LOD for physically-based real-time fire rendering
Tangvald, Lars (Master thesis, 2007)In this paper, I present a framework for implementing level of detail (LOD) for a 3d physically based fire rendering running on the GPU. While realistic fire rendering that runs in real time exists, it is generally not ... -
Improving Image Quality on The Setred Scanning Slit 3D Display
Haavik, Ola (Master thesis, 2007)Human depth perception can be described trough a set of depth cues, with binocular parallax being the most important. While a 2D display can show some depth cues, only 3D displays can give binocular parallax. One type of ... -
Improving the robustness of neural networks for time series forecasting through augmentationswith specific characteristics
Kjærnli, Håkon Slåtten (Master thesis, 2021)Nevrale nettverk er sett på som en toppmoderne metode i mange oppgaver som handler om mønstergjenkjenning, som bildeklassifisering og maskinoversettelse. Likevel har det blitt vist nevrale nettverk ofte produserer prediksjoner ... -
Improving User Experience of Indoor Maps Through Merging of Rooms
Normann, Morten Alver; Njærheim, Helmer Råby Schaug (Master thesis, 2017)The field of indoor map representation is an emerging field of research, contrary to outdoor maps, which has been under research for decades. A lot of focus in indoor maps has been on indoor positioning. However, map ... -
Interactive removal of outlier points in latent variable models using virtual reality
Aurstad, Tore (Master thesis, 2005)This report investigates different methods in computer graphics and virtual reality that can be applied to develop a system that provides analysis for the changes that occur when removing outlier points in plots for principal ... -
Leveraging Turbine-Level Data in a Deep Learning Approach for Wind Power Forecasting
Rommetveit, Herman; Kleppe, Lars Martin (Master thesis, 2021)Abstract will be available on 2024-06-18 -
Leveraging turbine-level data in a deep learning approach for wind power forecasting
Rommetveit, Herman; Kleppe, Lars Martin (Master thesis, 2021)Abstract will be available on 2024-06-18 -
LSTM Hybrid Model for Water Reservoir Inflow Forecasting, a Comparison Between Black Box- and Interpretable Hybrid Models
Osberg, Magnus Myrmo (Master thesis, 2020)Norges innsjøer oppnådde over 31GW innstallert vannkraftskapasitet, og produserte over 144 TWh ren kraft i 2016 i følge International Hydropower Association. Denne avhandlignen vurderer 9 hybridmodeller for prediksjon av ... -
Neural Ordinary Differential Equations for Forecasting in the Energy Sector
Borg, Stefan Artur Sobczyszyn (Master thesis, 2019)Nevrale Ordinære Differentiallikninger (NODE) [Chen et al., 2018] er en ny familie av nevrale nettverk som eksplisitt modellerer nettverkets skjulte tilstand som et dynamisk system, og løser dette systemet ved å bruke en ... -
Out-of-the-Box Reproducibility: A Survey of Machine Learning Platforms
Isdahl, Richard Juul; Gundersen, Odd Erik (Chapter, 2019)Even machine learning experiments that are fully conducted on computers are not necessarily reproducible. An increasing number of open source and commercial, closed source machine learning platforms are being developed ... -
Performing reproductions to understand the state of reproducibility in current AI research
Mølnå, Martin; Cappelen, Odd (Master thesis, 2018)In the last few years, the issue of reproducibility has gained increased attention in many scientific fields, including Artificial Intelligence (AI). Reproducibility of published results is a key concept of the scientific ... -
Physically Based Simulation and Visualization of Fire in Real-Time using the GPU
Rødal, Knut Erik Samuel; Storli, Geir (Master thesis, 2006)Fire is a powerful natural effect which can greatly enhance the immersion of virtual environments and games. In this thesis we describe the theory and GPU implementation of a physically based approach for simulating and ... -
References to Artificial Intelligence in Canada's Court Cases
Intahchomphoo, Channarong; Vellino, André; Gundersen, Odd Erik; Tschirhart, Christian; Shaaban, Eslam (Peer reviewed; Journal article, 2020)Artificial intelligence (AI) is a widely discussed topic in many fields including law. Legal studies scholars, particularly in the domain of technology and internet law, have expressed their hopes and concerns regarding ... -
Reports of the workshops held at the 2019 aaai conference on artificial intelligence
Barash, Guy; Castillo-Effen, Mauricio; Chhaya, Niyati; Clark, Peter; Espinoza, Huáscar; Farchi, Eitan; Geib, Christopher; Gundersen, Odd Erik; hÉigeartaigh, Seán Ó.; Hernández-Orallo, José; Hori, Chiori; Huang, Xiaowei; Jaidka, Kokil; Kapanipathi, Pavan; Keren, Sarah; Kim, Seokhwan; Lanctot, Marc; Lange, Danny; Martinez, David; Mattar, Marwan; Mausam, Mausam; Mcauley, Julian; Michalowski, Martin; Mirsky, Reuth; Mottaghi, Roozbeh; Osborn, Joseph C.; Pérolat, Julien; Schmid, Martin; Shaban-Nejad, Arash; Shehory, Onn; Srivastava, Biplav; Streilein, William; Talamadupula, Kartik; Togelius, Julian; Yoshino, Koichiro; Zhang, Quanshi; Zitouni, Imed (Journal article, 2019) -
The Reproducibility Crisis Is Real
Gundersen, Odd Erik (Peer reviewed; Journal article, 2020)The reproducibility crisis is real, and it is not only the field of psychology that has to deal with it. All the sciences are affected; the field of artificial intelligence is not an exception. -
Reproducibility of the Top-Performing Methods in the M4 Competition
Soleim, Maria (Master thesis, 2020)Reproduserbarhet har nylig fått økt oppmerksomhet innen kunstig intelligens. Selv om det hevdes at kunstig intelligens har en reproduserbarhetskrise, er dette ennå ikke bekreftet om tidsserieprognoser. Denne studien tar ...