Blar i NTNU Open på forfatter "Downing, Keith"
-
A Committee of One - Using Dropout for Active Learning in Deep Networks
Gammelsæter, Martin (Master thesis, 2015)In many of the problem domains typically tackled by deep learning, data is plentiful and cheap but labeling of the data is tedious and expensive. Letting a model actively select the data instances it is uncertain about ... -
A comparison of feature functions for Tetris strategies
Amundsen, Jonas Balgaard (Master thesis, 2014)Finding optimal strategies for the game of Tetris is an interesting NP-complete problem that has attracted several AI researchers. Their approaches display subtle variations in the implementation details, with unclear ... -
A Hybrid Topological and Geometrical Robot Mapping Approach
Nordstoga, Aasmund (Master thesis, 2009)Robotic mapping systems are traditionally separated into the metric and the topological paradigm. The metric approach provides geometrical accuracy, but is fragile because it is bounded in an absolute coordinate system and ... -
A semi-supervised approach to bird song classification
Caprioli, Emanuele (Master thesis, 2022)Økosystemer har sett mer dramatiske endringer enn noen annen gang I menneskets historie. Bioindikatorer som fugler overvåkes av ornitologer, for screening av miljøets kvalitet. Dyplæringsmetoder har produsert lovende ... -
Adaptive Behaviour Based Robotics using On-Board Genetic Programming
Kofod-Petersen, Anders (Master thesis, 2002)This thesis investigates the use of Genetic Programming (GP) to evolve controllers for an autonomous robot. GP is a type of Genetic Algorithm (GA) using the Darwinian idea of natural selection and genetic recombination, ... -
Adaptive Robotics
Fjær, Dag Henrik; Massali, Kjeld Karim Berg (Master thesis, 2009)This report explores continuous-time recurrent neural networks (CTRNNs) and their utility in the field of adaptive robotics. The networks herein are evolved in a simulated environment and evaluated on a real robot. The ... -
Adaptive Robotics: A behavior-based system for control of mobile robots
Johansen, Maria (Master thesis, 2010)This report will explore behavior-based robotics and relevant AI techniques. A system for autonomous control of mobile robots inspired by behavior-based robotics, in particular Rodney Brooks' subsumption architecture, have ... -
Alain Pétrowski and Sana Ben-Hamida: Evolutionary Algorithms
Downing, Keith (Journal article, 2018) -
An Artificial Immune System Approach to Preserving Security in Computer Networks
Ranang, Martin Thorsen (Master thesis, 2002)It is believed that many of the mechanisms present in the biological immune system are well suited for adoption to the field of computer intrusion detection, in the form of artificial immune systems. In this report mechanisms ... -
Analysing the influence of policy architecture choice on generalizing to new environments in deep reinforcement learning
Grande, Johannes Austbø (Master thesis, 2020)Generalisering er evnen til å overføre kunnskap fra et kjent problem til et ukjent problem. Det er noe som i det siste har fått mye oppmerksomhet innen dyp ''Reinforcement Learning'' (RL), og har ført til både raskere ... -
Artificial intelligence in the game of Quoridor
Birketvedt, Alfred (Master thesis, 2019)I de siste ti˚arene har brettspill f˚att mye oppmerksomhet innenfor datavitenskapen og kunstig intelligens. Denne masteroppgaven setter søkelys p˚a kunstig intelligens i Quoridor som er et nullsum-spill for to spillere. ... -
Artificial Intelligence Techniques in Real-Time Strategy Games - Architecture and Combat Behavior
Stene, Sindre Berg (Master thesis, 2006)The general purpose of this research is to investigate the possibilities offered for the use of Artificial Intelligence theory and methods in advanced game environments. The real-time strategy (RTS) game genre is investigated ... -
Artificial Neural Networks as a Monitoring System in Linux
Grønnesby, Øyvind (Master thesis, 2007)This thesis attempts to show how artificial neural networks can be used to implement computer monitoring systems based on internal state in the operating system running on the computer. Through experiments it will show how ... -
Automated Pollen-Grain Counting
Gyllenhammar, Fredrik (Master thesis, 2021)Denne oppgaven utforsker hvodan CNN baserte objektdeteksjonsmodeler kan bruker til å lokalisere of klassifisere pollenkorn ved hjelp av mikroskopisk bilde data. Telling av pollen er en sentral metode innen mange forskellige ... -
Automatic Configuration for Collective Construction: Automatic parameter setting for response threshold agents in collective construction
Braseth, Jørgen (Master thesis, 2007)NA -
Building a platform for exploring and visualizing deep convolutional networks
Barsch, Ole Øystein; Eilertsen, Odin (Master thesis, 2018)Deep artificial neural networks are showing a lot of promise when it comes to tasks involving images, such as object recognition and image classification. In recent years, there has been a steady increase in computing ... -
Classifying Glyphs: Combining Evolution and Learning
Rødland, Tiril Anette Langfeldt (Master thesis, 2011)This dissertation investigates the classification capabilities of artificial neural networks (ANNs). The goal is to generalize over the features of a writing system, and thus classify the writing system of a previously ... -
Combining offline and online learning in developing an adaptive controller for a simulated car racing environment
Corneliussen, Snorre Christoffer; Westergaard, Magnus (Master thesis, 2011)This report presents the work done to develop an autonomous driverfor the Simulated Car Racing Championship (SCRC), a competition incomputational intelligence based on The Open Racing Car Simulator(TORCS). Autonomous race ... -
Contributions to centralized dynamic channel allocation reinforcement learning agents
Sørnes, Torstein (Master thesis, 2018)We introduce a domain-specific policy improvement operator for reassigning channels during call hand-offs with the intent of reducing hand-off blocking probability. We construct an RL agent for maximizing average grid ... -
Cycle GANs for Forgery Detection
Jonsson, Haakon Johansen (Master thesis, 2021)Med den økende egenskapene til dype læringsmodeller blir bekymringene reist om bruk av maskinlæring som et verktøy for å generere falsk media. Dette gjøres vanligvis ved hjelp av generative nevrale nettverksarkitekturer ...