Blar i NTNU Open på forfatter "Downing, Keith"

Viser treff 61-80 av 91

    • Parallelization of Artificial Spiking Neural Networks on the CPU and GPU 

      Vekterli, Tor Brede (Master thesis, 2009)
      Conventional artificial neural networks have traditionally faced inherent problems with efficient parallelization of neuron processing. Recent research has shown how artificial spiking neural networks can, with the ...

    • Quantifying Environmental Diversity in Reinforcement Learning 

      Jørgensen, Jonathan (Master thesis, 2020)
      Å løse flere oppgaver med den samme agenten er en viktig problemstilling i reinforcement learning. I dette prosjektet utforsker vi konseptet variasjon i problem-sett. For å måle dette presenteres en algoritme for å ...

    • Real Time Intersection Management using a Multiobjective Evolutionary Algorithm 

      Solaas, Jostein Aune; Dissen, Håkon Ørstavik (Master thesis, 2016)
      The purpose of this thesis is to investigate the real time use of a Multiobjective Evolutionary Algorithm (MOEA) for intersection management. Intersection managers (IMs) using deterministic methods for real time intersection ...

    • Reconstruction of hepatic vessels from CT scans 

      Eidheim, Ole Christian (Master thesis, 2005)
      Deriving liver vessel structure from CT scans manually is time consuming and error prone. An automatic procedure that could help the radiologist in her analysis is therefore needed. We present two algorithms to preprocess ...

    • Reducing catastrophic forgetting in neural networks using slow learning 

      Vik, Mikael Eikrem (Master thesis, 2006)
      This thesis describes a connectionist approach to learning and long-term memory consolidation, inspired by empirical studies on the roles of the hippocampus and neocortex in the brain. The existence of complementary learning ...

    • Reducing catastrophic forgetting in neural networks using slow learning 

      Vik, Mikael Eikrem (Master thesis, 2006)
      This thesis describes a connectionist approach to learning and long-term memory consolidation, inspired by empirical studies on the roles of the hippocampus and neocortex in the brain. The existence of complementary learning ...

    • Reduction of search space using group-of-experts and RL. 

      Anderson, Tore Rune (Master thesis, 2007)
      This thesis is testing out the group of experts regime in the context of reinforcement learning with the aim of reducing the search space used in reinforcement learning. Having tested different abstracion levels with this ...

    • Relevant Concepts of and a Framework for Conceptual Representations based on Connectionism 

      veflingstad, henning (Master thesis, 2007)
      In this thesis we have investigated what concepts are and how they may be represented. We have seen that conceptual representations can be achieved by employing distributed representations in a hidden layer of a neural ...

    • Remembering Past States using Long Short Term Memory Neural Networks 

      Sjonfjell, Vegard Aksland (Master thesis, 2014)
      This project explores the ability of Recurrent Neural Networks (RNNs) to memorize previous input states in time series problems.A type of RNN called Long Short Term Memory (LSTM), which is designed specifically to be able ...

    • Reservoir Production Optimization Using Genetic Algorithms and Artificial Neural Networks 

      Andersen, Mats Grønning (Master thesis, 2009)
      This master's thesis has investigated how methods from artificial intelligence (AI) can be used to perform and augment production optimization of sub-sea oil reservoirs. The methods involved in this work are genetic ...

    • Segmentation of repetitions and sets in weight lifting workouts with LSTM networks 

      Børtnes, Snorre (Master thesis, 2019)

    • Self-Assembling to Improve Performance in Swarm Robotics 

      Halvorsen, Joachim; Seilen, Hege Beate (Master thesis, 2014)
      This thesis gives a brief introduction to the field of swarm robotics, and investigates the advantages of using self-assembling for swarm robots in difficult environments. The current research in swarm robotics has already ...

    • Self-assembly Mechanisms for Evolutionary Robotics 

      Tannum, Christopher Jeffrey; Jakobsen, Eirik (Master thesis, 2016)
      In recent study, an increasing amount of time has been spent researching complex systems due to the traditional Von Neumann architecture lacking sufficient efficiency. A specific complex system which has been growing in ...

    • Sequence learning in a model of the basal ganglia 

      Søiland, Stian (Master thesis, 2006)
      This thesis presents a computational model of the basal ganglia that is able to learn sequences and perform action selection. The basal ganglia is a set of structures in the human brain involved in everything from action ...

    • Sequence learning in a model of the basal ganglia 

      Søiland, Stian (Master thesis, 2006)
      This thesis presents a computational model of the basal ganglia that is able to learn sequences and perform action selection. The basal ganglia is a set of structures in the human brain involved in everything from action ...

    • Short- and Long-term Memory: A Complementary Dual-network Memory Model 

      Berg, William Peer (Master thesis, 2016)
      In recent years, the possible applications of artificial intelligence (AI) and deep learning have increased drastically. However, the algorithms which constitute the learning mechanisms in deep learning are based largely ...

    • Simulation of Salamander Locomotion 

      Viazzi, Stefano (Master thesis, 2008)
      As part of the research on locomotion controller that aims to produce robots whose design is inspired by Nature, this thesis intends to develop a simulator of the salamander locomotion. It investigates, in particular, what ...

    • Steps towards an empirically responsible AI: a methodological and theoretical framework 

      Svedberg, Peter O.S. (Master thesis, 2004)
      Initially we pursue a minimal model of a cognitive system. This in turn form the basis for the development of amethodological and theoretical framework. Two methodological requirements of the model are that explanation be ...

    • Supervised Learning of Complex Activities using Wearable Sensors 

      Aders, Lars Martin; Syversen, Ola Richard (Master thesis, 2020)
      Klassifisering av raske komplekse bevegelser er en stor utfordring innen bevegelsesgjenkjenning. I mange sportsgrener er det utviklet enheter som innhenter forskjellige typer data, for så å lage et sammendrag av en gjennomført ...

    • Supervised Learning of Complex Activities using Wearable Sensors 

      Aders, Lars Martin; Syversen, Ola Richard (Master thesis, 2020)
      Klassifisering av raske komplekse bevegelser er en stor utfordring innen bevegelsesgjenkjenning. I mange sportsgrener er det utviklet enheter som innhenter forskjellige typer data, for så å lage et sammendrag av en gjennomført ...