Sökning: "matematik träning"

Visar resultat 6 - 9 av 9 avhandlingar innehållade orden matematik träning.

  1. 6. Topics on Generative Models in Machine Learning

    Författare :Carl Ringqvist; Henrik Hult; Thomas Schön; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : Latent variable models have been extensively studied within the field of machine learning in recent years. Especially in combination with neural networks and training through back propagation, they have proven successful for a variety of tasks; notably sample gener- ation, clustering, disentanglement and interpolation. LÄS MER

  3. 7. Topics on Large Deviations in Artificial Intelligence

    Författare :Adam Lindhe; Henrik Hult; Jimmy Olsson; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Mathematical Statistics; Matematisk statistik;

    Sammanfattning : Artificial intelligence has become one of the most important fields of study during the last decade. Applications include medical sciences, autonomous vehicles, finance and everyday life. Therefore the analysis of convergence and stability of these algorithms is of utmost importance. LÄS MER

  4. 8. On Medical Image Segmentation With Noisy Labels

    Författare :Marcus Nordström; Henrik Hult; Atsuto Maki; Fredrik Kahl; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Medical image segmentation; image segmentation; machine learning; supervised learning; label noise; Sörensen-Dice coefficient; soft-Dice; Medicinsk bildsegmentering; bildsegmentering; maskininlärning; övervakat lärande; annoteringsbrus; Sörensen-Dice koefficienten; soft-Dice; Tillämpad matematik och beräkningsmatematik; Applied and Computational Mathematics; Mathematical Statistics; Matematisk statistik;

    Sammanfattning : It is well known that data sets used for training and testing automatic medical image segmentation methods often contain a lot of label noise. Such noise affects the performance of the methods and has been subject to a lot of research. LÄS MER

  5. 9. Motorik, koncentrationsförmåga och skolprestationer : en interventionsstudie i skolår 1-3

    Författare :Ingegerd Ericsson; Utbildningsvetenskap; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Physical training; physical education; motor training; Cognition; motor skill observations; motorial learning; sport; Idrott; gymnastik; motorisk inlärning; academic achievements;

    Sammanfattning : The aim of this thesis is to study effects of an extension of physical education/activity and motor training on motor skills, attention and cognition during a period of three years. Another aim is to develop a test, MUGI observationsschema, which could be useful in charting motor skills of school pupils. LÄS MER