Blar i NTNU Open på forfatter "Downing, Keith"

Viser treff 41-60 av 91

    • Fuzzy Oscillations: a Novel Model for Solving Pattern Segmentation 

      Solbakken, Lester Johan (Master thesis, 2009)
      In this thesis we develop a novel network model that extends the traditional artificial neural network (ANN) model to include oscillatory behaviour. This model is able to correctly classify combinations of previously learned ...

    • Handling Autonomous Robot Scheduling as an Optimization Problem 

      Rugsveen, Nils Inge; Bakke, Alexander (Master thesis, 2016)
      This dissertation investigates the possibility to model the behavior of an agent solving a complex robotic scheduling task, mission 7a of the International Aerial Robotics Competition, as an optimization problem known as ...

    • Implementing Boids behaviors on the ChIRP robots 

      Lam, Hong-Dang (Master thesis, 2015)
      This thesis gives a brief overview to the field of swarm robotics and investigates how robots are able to flock together using the Boids algorithm. Four robots will be used in this thesis. Swarm robotics is an emergent ...

    • Incorporating Labor Division into Ant Colony Optimization 

      Grimnes, Jørgen Kjeldstad; Hovland, Jakob (Master thesis, 2016)
      Ant colony optimization (ACO) is a constructivistic and population-based metaheuristic for solving combinatorial optimization problems inspired by how real ants use pheromones to find shortest paths. Like other metaheuristics ...

    • Incremental Evolutionary Methods for Automatic Programming of Robot Controllers 

      Petrovic, Pavel (Doktoravhandlinger ved NTNU, 1503-8181; 2007:228, Doctoral thesis, 2007)
      The aim of the main work in the thesis is to investigate Incremental Evolution methods for designing a suitable behavior arbitration mechanism for behavior-based (BB) robot controllers for autonomous mobile robots performing ...

    • Incrementally Evolving a Dynamic Neural Network for Tactile-Olfactory Insect Navigation 

      Thuv, Øyvin Halfdan (Master thesis, 2007)
      This Masters thesis gives a thorough description of a study carried out in the Self-Organizing Systems group at the NTNU. Much {AI research in the later years has moved towards increased use of representationless strategies ...

    • Inferring Phylogenies Using Evolutionary Algorithms: A maximum likelihood approach for constructing phylogenetic trees from molecular data 

      Hamberg, Erlend Heggheim (Master thesis, 2011)
      This thesis has evaluated the use of the computationally expensivemaximum-likelihood (ML) method coupled with an evolutionaryalgorithm (EA) for the problem of inferring evolutionaryrelationships among species (phylogenies) ...

    • Information Theory for Analyzing Neural Networks 

      Sørngård, Bård (Master thesis, 2014)
      The goal of this thesis was to investigate how information theory could be used to analyze artificial neural networks. For this purpose, two problems, a classification problem and a controller problem were considered. The ...

    • Investigating the Effect of Samples per Class and Number of Classes for Capsule Networks' Performance 

      Bjørnøy, Håvard (Master thesis, 2020)
      Bildeanalyse er allestedsnærværende i daglige tjenester, for eksempel ansiktsgjenkjenning for å låse opp telefonen, QR-koder og algoritmer for bildeforbedring. Store bransjer som autonome kjøretøy, autonome lager, samlebånd ...

    • Investigating the Generality of Deep Learning 

      Haaland, Torgeir (Master thesis, 2016)
      This thesis investigates how general the knowledge stored in deep-Q-networks are. This general knowledge can be used to reduce the training time of deep neural networks. Recent advances in the field of deep reinforcement ...

    • Investigating the use of CycleGANs in handwritten forgery detection 

      Kristiansen, Kevin (Master thesis, 2021)
      Generative modeller som implementerer Kunstige nevrale netverk(ANNs) for bildegenerering har sett store fremskritt de siste årene. Generative Adversarial Networks(GANs) er en teknikk som har sett særlig stor utvikling, og ...

    • Kunstige nevrale nettverk for deteksjon av aksjonspotensialer i kalsiumbildedata 

      Antonsen, Mikkel (Master thesis, 2016)
      I oppgaven blir forskjellige nettverksarkitekturer og regulariseringsteknikker for kunstige nevrale nettverk undersøkt for om de kan brukes til å finne den underliggende årsaken til kalsiumbildedata. En arkitektur som ...

    • Learning event-driven time series with phased recurrent neural networks 

      Haartveit, Are; Husum, Harald (Master thesis, 2018)
      We explore machine learning algorithms for time series data, particularly recurrent neural networks. For us, the most interesting methods are ones for handling long duration time series, where the sampling of data channels ...

    • Learning neural representations for the processing of temporal data in deep neutral networks 

      Måløy, Håkon (Doctoral theses at NTNU;2023:6, Doctoral thesis, 2023)
      Ever since the third spring of artificial intelligence a decadeago, representation learning through deep neural networks hasbeen the dominating approach for most research in machinelearning. However, typical deep neural ...

    • Modeling Place Cells with a Biological Plausible Artificial Neural Network 

      Aamodt, Kjetil (Master thesis, 2011)
      The purpose of this paper is to use an artificial neural network to simulate the generation of place cell in the mammal hippocampus. These cells are a result of sensory stimuli input to animals like the rat. In this paper ...

    • Network based pandemic modeling 

      Orvik, Alexander (Master thesis, 2023)
      Beregningsbasert epidemiologi er et stort felt med mange tilnærminger og verktøy for modellering av pandemier. Disse tilnærmingene varierer fra statistisk analyse og differensialligninger, agentbasert modellering og til ...

    • Neural Net Controller for a Snake Robot 

      Dale, Eirik Skjeggestad (Master thesis, 2014)
      When we re talking about the field of robotics, one of the key components is the controller for the robots. The focus has recently begun shifting away from the traditional wheeled robots, into biologically inspired robots. ...

    • Neural Network Models of Mathematical Cognition 

      Sabathiel, Silvester (Doctoral theses at NTNU;2023:91, Doctoral thesis, 2023)

    • Optimizing Echo State Networks for Learning Temporal Sequences 

      Irgens, Terje (Master thesis, 2009)
      Echo state networks are a new type of artificial neural network. It is created of a recurrent neural network with input, output and back weights. What separates echo state networks from other recurrent neural networks is ...

    • OptiNet: AMD Detection Network 

      Hanssen, Stian Rikstad (Master thesis, 2019)
      Det medisinske fagfeltet utforsker flere og flere automatiske teknikker for å hjelpe fagpersoner i sitt arbeid. I de siste årene, har kunstige nevrale nettverk funnet suksess i et stort antall fagfelt med ytelse på likt ...