• A Continuous Approach to Controllable Text Generation using Generative Adversarial Networks 

      Helgøy, Dag Inge; Lund, Markus (Master thesis, 2017)
      The challenges of training generative adversarial network (GAN) to produce discrete tokens, have seen a considerable amount of work in the past year. However, the amount of successful work on applying deep generative models ...
    • A deep network model for paraphrase detection in short text messages 

      Agarwal, Basant; Ramampiaro, Heri; Langseth, Helge; Ruocco, Massimiliano (Journal article; Peer reviewed, 2018)
      This paper is concerned with paraphrase detection, i.e., identifying sentences that are semantically identical. The ability to detect similar sentences written in natural language is crucial for several applications, such ...
    • A Flexible Software System for Learning Bayesian Networks from data 

      Aabakken, Trond (Master thesis, 2007)
      Bayesian networks, also referred to as belief networks, originates from the artificial intelligence field where they were used to reason about uncertain knowledge. They differ from other knowledge representation schemes ...
    • A Novel Algorithmic Trading Framework Applying Evolution and Machine Learning for Portfolio Optimization 

      Mikelsen, Stian; Andersen, André Christoffer (Master thesis, 2012)
      The goal of this thesis is to implement an automated trading system able to outperform the benchmark uniform buy-and-hold strategy. Performance is measured in term of multiple risk and return measures. A comprehensive ...
    • A Novel Algorithmic Trading Framework Applying Evolution and Machine Learning for Portfolio Optimization 

      Mikelsen, Stian; Andersen, André Christoffer (Master thesis, 2012)
      The goal of this thesis is to implement an automated trading system able to outperform the benchmark uniform buy-and-hold strategy. Performance is measured in term of multiple risk and return measures. A comprehensive ...
    • A Parallel Algorithm for Bayesian Network Structure Learning from Large Data Sets 

      Madsen, Anders L.; Jensen, Frank; Salmeron, Antonio; Langseth, Helge; Nielsen, Thomas D. (Journal article; Peer reviewed, 2017)
      This paper considers a parallel algorithm for Bayesian network structure learning from large data sets. The parallel algorithm is a variant of the well known PC algorithm. The PC algorithm is a constraint-based algorithm ...
    • A Review of Inference Algorithms for Hybrid Bayesian Networks 

      Salmeron, Antonio; Rumi, Rafael; Langseth, Helge; Nielsen, Thomas D.; Madsen, Anders L. (Journal article; Peer reviewed, 2018)
      Hybrid Bayesian networks have received an increasing attention during the last years. The difference with respect to standard Bayesian networks is that they can host discrete and continuous variables simultaneously, which ...
    • Activity Recognition for Stroke Patients 

      Vågeskar, Eirik (Master thesis, 2017)
      Stroke is a disruption in the blood flow to the brain which may lead to a death of brain cells. More than 12000 Norwegians experience a stroke each year. Survivors often suffer lasting movement disabilities, which affect ...
    • AMIDST: A Java toolbox for scalable probabilistic machine learning 

      Masegosa, Andres; Martinez, Ana M.; Ramos-López, Dario; Cabañas, Rafael; Langseth, Helge; Nielsen, Thomas D.; Madsen, Anders L. (Journal article; Peer reviewed, 2018)
      The AMIDST Toolbox is an open source Java software for scalable probabilistic machine learning with a special focus on (massive) streaming data. The toolbox supports a flexible modelling language based on probabilistic ...
    • Analysis of Driving Data and Safe Driving Scoring Algorithms 

      Rosmo, Knut Erik (Master thesis, 2018)
      Traditionally, car insurance companies have had to rely on very rough estimates of risk posed by customers, based on age, gender, postal code, etc. Newer technologies such as the smart phone, custom made telematics boxes ...
    • Analyzing concept drift: A case study in the financial sector 

      Masegosa, Andres; Martinez, Ana M.; Ramos-López, Dario; Langseth, Helge; Nielsen, Thomas D.; Salmeron, Antonio (Journal article; Peer reviewed, 2020)
      In this paper, we present a method for exploratory data analysis of streaming data based on probabilistic graphical models (latent variable models). This method is illustrated by concept drift tracking, using financial ...
    • Application of data-driven models in the analysis of marine power systems 

      Swider, Anna; Langseth, Helge; Pedersen, Eilif (Peer reviewed; Journal article, 2019)
      Computational thinking and coding are becoming an integral part of K-12 education, with female students being underrepresented in such subjects. The proliferation of technological tools and programming environments offers ...
    • Applications of artificial potential fields for real time strategy games: Troop formations and movements used trained potential functions 

      Hansen, Finn Robin Kåveland (Master thesis, 2012)
      This thesis describes the effort of adapting potential field methods towards man-aging groups of units in real-time strategy game like environments. The focus is ondiscovering the suitability for this technology to create ...
    • Automated Techniques for estimating Customer Value and Causal Models of Customer Satisfaction 

      Persett, Tor-Helge; Henriksen, Stig (Master thesis, 2009)
      In the competitive business environment of today, knowing which customers to target,and how, is essential for maximizing the return of the invested resources.In order to accomplish this we need a way of estimating who will ...
    • Automatic stock market trading based on Technical Analysis 

      Larsen, Fredrik (Master thesis, 2007)
      The theory of technical analysis suggests that future stock price developement can be foretold by analyzing historical price fluctuations and identifying repetitive patterns. A computerized system, able to produce trade ...
    • Autonomous Localization and Tracking for UAVs using Kalman Filtering 

      Jansen, Johan (Master thesis, 2014)
      Quadcopters and other drones have become more popular as they become more af- fordable and easier to use. As the accessibility increases, people discover new fields of application and one such potential use is for filming ...
    • Bayesian networks with applications in reliability analysis 

      Langseth, Helge (Dr. ingeniøravhandling, 0809-103X; 2002:121, Doctoral thesis, 2002)
      A common goal of the papers in this thesis is to propose, formalize and exemplify the use of Bayesian networks as a modelling tool in reliability analysis. The papers span work in which Bayesian networks are merely used ...
    • Beating the bookmakers - Using artificial neural networks to profit from football betting 

      Borøy-Johnsen, Simon (Master thesis, 2017)
      Artificial Neural Networks (ANNs) have throughout the years been used for several different purposes. Problems spanning from image classification to text generation have all been subject to ANNs. In this report, ANNs were ...
    • Classification of Marine Vessels using Sonar Data and a Neural Network 

      Gimse, Håkon (Master thesis, 2017)
      A submarine navigator have to keep track of surrounding ships in order to avoid collision and to gain a tactical advantage. This is currently done manually by a sonar operator, trained to listen through the water and ...
    • Collaborative Filtering for Recommending Movies 

      Bøe, Cecilie (Master thesis, 2007)
      There is a significant amount of ongoing research in the collaborative filtering field, with much of the research focusing on how to most accurately give item predictions to a user, based on ratings given by other users ...