Sökning: "Semi-supervised learning"

Visar resultat 16 - 20 av 78 uppsatser innehållade orden Semi-supervised learning.

  1. 16. Computer Vision in Fitness: Exercise Recognition and Repetition Counting

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Anna Barysheva; [2022]
    Nyckelord :Exercise classification; human action recognition; repetition counting; skeletal motion recognition; unsupervised machine learning; Övningsklassificering; igenkänning av mänsklig handling; upprepningsräkning; igenkänning av skelettrörelse; oövervakad maskininlärning;

    Sammanfattning : Motion classification and action localization have rapidly become essential tasks in computer vision and video analytics. In particular, Human Action Recognition (HAR), which has important applications in clinical assessments, activity monitoring, and sports performance evaluation, has drawn a lot of attention in research communities. LÄS MER

  3. 17. LaMOSNet: Latent Mean-Opinion-Score Network for Non-intrusive Speech Quality Assessment : Deep Neural Network for MOS Prediction

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Fredrik Cumlin; [2022]
    Nyckelord :Speech naturalness assessment; Speech quality assessment; Mean opinion score; Voice conversion challenge; Semi-supervised learning; Noisy labels.; Naturligt tal bedömning; Ljudkvalitetsbedömning; Medel bedömningsvärdet; Talkonverteringsutmaningen; Semi-övervakad inlärning; Varierande märkningar.;

    Sammanfattning : Objective non-intrusive speech quality assessment aimed to emulate and correlate with human judgement has received more attention over the years. It is a difficult problem due to three reasons: data scarcity, noisy human judgement, and a potential uneven distribution of bias of mean opinion scores (MOS). LÄS MER

  4. 18. A Systematic Study of Semi-Supervised Learning Based on Shapley Value Data Valuation

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Christie Courtnage; [2022]
    Nyckelord :;

    Sammanfattning : Semi-supervised learning algorithms seek to train prediction models on both labelled and unlabelled that outperform prediction models trained only on labelled data. Semi-supervised learning is often realised through the selection of unlabelled instances with predicted pseudo-labels. LÄS MER

  5. 19. Training a computer vision model using semi-supervised learning and applying post-training quantizations

    Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Författare :Albernn Vedin; [2022]
    Nyckelord :Machine learning; Object detection; Computer vision; Neural network; Semi-supervised learning; Post-training quantizations; Embedded systems; Electrical scooters;

    Sammanfattning : Electrical scooters have gained a lot of attention and popularity among commuters all around the world since they entered the market. After all, electrical scooters have shown to be efficient and cost-effective mode of transportation for commuters and travelers. LÄS MER

  7. 20. Sequential Anomaly Detection for Log Data Using Deep Learning

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Lina Hammargren; Wei Wu; [2021-06-14]
    Nyckelord :anomaly detection; recurrent neural network; long short-term memory; semi-supervised learning; seq2seq; transformer; unsupervised learning; log analysis;

    Sammanfattning : Abstract Software development with continuous integration changes needs frequent testing for assessment. Analyzing the test output manually is time-consuming and automating this process could be beneficial to an organization. LÄS MER