Sökning: "Evolutionary Computation"

Visar resultat 6 - 10 av 11 uppsatser innehållade orden Evolutionary Computation.

  1. 6. Evolving Text Classifier Using Genetic Programming

    Master-uppsats, Lunds universitet/Avdelningen för Biomedicinsk teknik

    Författare :Hoang Ngo; Ema Eminagic; [2020]
    Nyckelord :genetic programming; evolutionary algorithm; evolutionary computation; text classification; n-grams; natural language processing; Technology and Engineering;

    Sammanfattning : Text classification is one of the main tasks within the field of natural language processing, which has been growing significantly during the last decade with applications in different industries. Despite different approaches to text classification showing good results, such as Machine Learning and Deep Learning, their shortcomings give substance to the need for further research on other approaches. LÄS MER

  3. 7. Scaling the Evolution of Artificial Neural Networks in the Cloud

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Felix Runge; [2018]
    Nyckelord :;

    Sammanfattning : Deep Learning is one technique within the field of Machine Learning which is able to solve tasks such as Image Classification or Natural Language Processing. With its recent success, Deep Learning and therefore Artificial Neural Networks receive a high exposure. LÄS MER

  4. 8. Evolutionary Computation in Continuous Optimization and Machine Learning

    Kandidat-uppsats, Mälardalens högskola/Akademin för innovation, design och teknik

    Författare :Leslie Dahlberg; [2017]
    Nyckelord :evolutionary; algorithm; optimization;

    Sammanfattning : Evolutionary computation is a field which uses natural computational processes to optimize mathematical and industrial problems. Differential Evolution, Particle Swarm Optimization and Estimation of Distribution Algorithm are some of the newer emerging varieties which have attracted great interest among researchers. LÄS MER

  5. 9. Association Rules in Parameter Tuning : for Experimental Designs

    Magister-uppsats, Mittuniversitetet/Avdelningen för informations- och kommunikationssystem

    Författare :Henrik Hållén; [2014]
    Nyckelord :Evolutionary Computation; Evolutionary Algorithms; Data mining; association rules; parameter tuning; In- PUT; SPOT;

    Sammanfattning : The objective of this thesis was to investigate the possibility ofusing association rule algorithms to automatically generaterules for the output of a Parameter Tuning framework. Therules would be the basis for a recommendation to the user regardingwhich parameter space to reduce during experimentation. LÄS MER

  7. 10. Collision Detection and Overtaking Using Artificial Potential Fields in Car Racing game TORCS using Multi-Agent based Architecture

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datalogi och datorsystemteknik

    Författare :Muhammad Salman; [2013]
    Nyckelord :Artificial Potential Fields; TORCS; Simulated Car Racing Championship; Collision Detection; Overtaking;

    Sammanfattning : The Car Racing competition platform is used for evaluating different car control solutions under competitive conditions [1]. These competitions are organized as part of the IEEE Congress on Evolutionary Computation (CEC) and Computational Intelligence and Games Sym-posium (CIG). LÄS MER