Browsing NTNU Open by Author "Downing, Keith"

Now showing items 21-40 of 91

    • Deep Reinforcement Learning for Gripper Vector Estimation 

      Olsen, Thomas; Ottesen, Birk Midtbø (Master thesis, 2018)
      The problem of gripper vector estimation, also referred to as gripper pose estimation, is the problem of constructing a vector describing the pose of the end-effector of a robotic gripper, which enables it to grasp an ...

    • Deep Reinforcement Learning for Spatio-Temporal Wildlife Management 

      Singh, Anmol (Master thesis, 2023)
      De siste 50 årene har globale dyrelivsbestander opplevd betraktelig nedgang som har ført til en biologisk mangfoldskrise hvor et betydelig antall dyrearter har blitt utrydningstruet. Denne oppgaven tester ytelsen til ulike ...

    • Deep reinforcement Learning Using Monte-Carlo Tree Search for Hex and Othello 

      Bruåsdal, Henrik (Master thesis, 2020)
      Når Deepminds AlphaGo-program slo den menneskelige profesjonelle Go-spilleren Fan Hui i 2015 var dette et stort gjennombrudd for kunstig intelligens til spilling. Go hadde vist seg å motstå de teknikkene som lenge hadde ...

    • Detecting a Hidden Radio Frequency Transmitter in Noise based on Amplitude using Swarm Intelligence 

      Nordmoen, Jørgen Halvorsen (Master thesis, 2014)
      Radio Frequency transmitters are becoming ubiquitous. For instance people oftencarry around a mobile phone containing several such transmitters. Having theability to detect and locate such transmitters in noisy environments ...

    • Distribuerte evolusjonære mekanismer og organisering 

      Halvorsen, Tore (Master thesis, 2004)
      Oppgaven tar for seg noen av problemstillingene som oppstår hvis man forsøker å distribuere en evolusjon ut i flere parallelle prosesser. Den ser først og fremst på de ulike måtene subpopulasjoner kan kommunisere, og hvordan ...

    • Diversity Guided Adaptive Evolutionary Algorithm 

      Thafvelin, Nicolay N; Asplin, Julius Buset (Master thesis, 2015)
      Parameter tuning in Evolutionary Algorithms (EA) generally result in suboptimal choices of values because of the complex dependencies between the parameters. Furthermore, different scenarios during a run of the EA often ...

    • Dopamine modulated STDP and reinforcement learning in an embodied context 

      Andersen, Lars; Haus, Tormund Sandve (Master thesis, 2013)
      In recent years artificial neural networks have become increasing popular. New methods and ever increasing computational resources are turning second generation artificial neural networks into powerful tools. Most of the ...

    • Dynamic Scheduling for Autonomous Robotics 

      Ellefsen, Kai Olav (Master thesis, 2010)
      This project report describes a hybrid genetic algorithm that works as a schedule generator for a complex robotic harvesting task. The task is set to a dynamic environment with a robotic opponent, making responsiveness of ...

    • Evolution of Artificial Neural Networks for Othello Board State Evaluation 

      Westby, Petter (Master thesis, 2011)
      To make informed choices of encodings for Evolutionary Artificial Neural Networks, empirical data types of these is needed.In this thesis, the performance of a direct encoding specifying the weights of a fully connected ...

    • Evolutionary Robotics 

      Egeland, Jan Terje (Master thesis, 2010)
      In this report we have looked at the application of the evolutionary process applied to neural networks, and in particular the CTRNN network type. We have experimented with the network structure, network parameters and all ...

    • Evolving a 2D Model of an Eye using CPPNs 

      Storsveen, Anders (Master thesis, 2008)
      This papers uses CPPNs to evolve 2D models of an eye. These models are graded by a fitness function award high information retrieval. The papers shows resulting models with intersting properties and which are similar in ...

    • Evolving a roving-eye for go revisited 

      Mathisen, Bjørn Magnus (Master thesis, 2007)
      This thesis presents a further development of Neuroevolution of Augmenting topologies(NEAT)[21]. The author augments NEAT by parallelizing the fitness evaluation of the phenotypes enabling the method to be utilized on ...

    • Evolving Agent Swarms for Clustering,Patch Sorting, and Annular Sorting 

      Hartmann, Vegard (Master thesis, 2005)
      Colonies of social insects are capable of solving complex tasks that far exceed the abilities of each individual insect. The colonies do not use any supervisor or blueprint to organize their work, instead the solutions ...

    • Evolving Behaviour Trees: - Automatic Generation of AI Opponents for Real-Time Strategy Games 

      Hoff, Jonatan Wilhelm; Christensen, Hallvard Jore (Master thesis, 2016)
      Video games are a source of fun and enjoyment for millions of people across the globe. Artificial Intelligence (AI) is an essential part of many games and there is an increasing demand for ever more realistic computer ...

    • Evolving Controllers for Simulated Agricultural Scenarios Using Genetic Programming 

      Vatnar, Henrik (Master thesis, 2008)
      A lot of work in the agriculture world consists of guiding a vehicle on a field. The goal is to cover the entire field with e.g. a plow or a sowing machine. Today there are several systems available which assist the driver. ...

    • Evolving Deep Neural Networks using Genetic Algorithms 

      Børstad, Eivind (Master thesis, 2020)
      I denne masteroppgaven har nevroevolusjon blitt brukt for å automatisk utvikle de fleste av hyperparametrene for nevrale nett, som ellers må settes manuelt av bruker. Den foreslåtte metodologien skiller seg fra de fleste ...

    • Evolving Echo State Networks for Minimally Cognitive Unsupervised Learning Tasks 

      Stuan, Dag (Master thesis, 2013)
      This thesis investigates the use of Echo State Networks (ESNs) in unsupervised learning environments, byemploying Evolutionary Algorithms (EAs) to evolve ESNs to control an agent that performs a novel, minimally-cognitive ...

    • Evolving Predator Swarm Intelligence 

      Lillejordet, Fredrik (Master thesis, 2015)
      This master thesis investigates the evolution of predator swarm intelligence in predator- prey relationships. It aims to prove that we can evolve more efficient behavior than a set of simple rules in simulated environments. ...

    • Examining Remapping Phenomena in a Computational Model of the Hippocampus 

      Edvardsen, Vegard (Master thesis, 2014)
      The hippocampus is a brain structure known to be involved in high-level cognitive features such as memory and navigation. Spatially responsive cells in the hippocampal region, known as place cells and grid cells, have given ...

    • Exploring Self-Supervised Learning for Bird Vocalization Classification 

      Norum, Ole-Magnus Vian (Master thesis, 2023)
      Fugler har en essensiell rolle i økosystemet de tilhører og kan bli brukt som indikasjonsarter for å vurdere helsen til et økosystem. På grunn av disse faktorene, har fugleartmonitorering blitt en mulig strategi for å ...