Blar i NTNU Open på forfatter "Løvlid, Rikke Amilde"
-
A Novel Method for Training an Echo State Network with Feedback-Error Learning
Løvlid, Rikke Amilde (Journal article; Peer reviewed, 2013)Echo state networks are a relatively new type of recurrent neural networks that have shown great potentials for solving non-linear, temporal problems. The basic idea is to transform the low dimensional temporal input into ... -
Automating Behaviour Modelling for Computer Generated Forces - Evolving Behaviour Trees with Observational Learning
Berthling-Hansen, Gabriel; Morch, Eivind (Master thesis, 2018)Computer generated forces are simulated entities that are used in simulation based training and decision support in the military. The behaviour of these simulated entities should be as realistic as possible, so that the ... -
Automating Behaviour Tree Generation for Simulating Troop Movements
Berthling-Hansen, Gabriel; Morch, Eivind; Løvlid, Rikke Amilde; Gundersen, Odd Erik (Chapter, 2018)Computer generated forces are simulated units that are used in simulation based training and decision support in the military. These simulations are used to help trainees build a mental model of how different scenarios ... -
Internal Models as Echo State Networks: Learning to Execute Arm Movements
Løvlid, Rikke Amilde (Doktoravhandlinger ved NTNU, 1503-8181; 2013:335, Doctoral thesis, 2013)As robots are becoming more and more complex, with higher degrees-of-freedom, lighter limbs, and springy joints, it becomes harder to control their movements. New approaches, inspired from neuroscience, are attracting ... -
Recurrent Neural Network for Learning and Reproducing Movements
Løvlid, Rikke Amilde (Master thesis, 2007)In this thesis I study how movements can be learned and stored by a recurrent neural network. Also I investigate how a movement can be associated with an external context, and wether this can be used to produce movements ...