Sökning: "datorprogram för matematik"

Visar resultat 1 - 5 av 23 uppsatser innehållade orden datorprogram för matematik.

  1. 1. Assessing the Efficiency of COLMAP, DROID-SLAM, and NeRF-SLAM in 3D Road Scene Reconstruction

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Marcus Ascard; Farjam Movahedi; [2023]
    Nyckelord :3D reconstruction; Visual SLAM; Pose evaluation; Point cloud evaluation; Road scenes; Technology and Engineering;

    Sammanfattning : 3D reconstruction is a field in computer vision which has evolved rapidly as a result of the recent advancements in deep learning. As 3D reconstruction pipelines now can run in real-time, this has opened up new possibilities for teams developing Advanced Driver Assistance Systems (ADAS), which rely on the camera system of the vehicle to enhance the safety and driving experience. LÄS MER

  3. 2. Digitala verktyg på gymnasiet : En kvalitativ studie om hur matematiklärare använder digitala verktyg i matematikundervisningen

    Uppsats för yrkesexamina på avancerad nivå, KTH/Lärande

    Författare :Mohammad Ghasemi; [2022]
    Nyckelord :Digital knowledge; Digital tools; Mathematics teaching; Digitala kunskaper; Digitala verktyg; Matematikundervisning;

    Sammanfattning : Denna studie berör hur gymnasielärare använder sig av digitala verktyg i matematikundervisning samt ger rekommendationer hur digitala verktyg kan användas. I denna studie har lärare beskrivit fördelar och nackdelar med digitala verktyg i matematikundervisning. LÄS MER

  4. 3. Data Augmentation to Improve Cross-Domain Generalization in Deep Learning MRI Segmentation

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Rasmus Helander; [2021]
    Nyckelord :deep learning; medical imaging; mri; segmentation; data augmentation; cyclegan; noisy labels; Mathematics and Statistics;

    Sammanfattning : Semantic segmentation of medical images is an important task with many applications. However, manually delineating 3D images is time-consuming and the demand for automation is high. For many image segmentation tasks, deep learning has provided state-of-the-art results. LÄS MER

  5. 4. ERA: Evolution of Residual Architectures

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Samuel Lundberg; [2020]
    Nyckelord :Neural Architecture Search; Automated Machine Learning; Black-box Optimization; Residual Networks; Convolutional Networks; Image Classification; Neuro-Evolutionary Computing; Technology and Engineering;

    Sammanfattning : This thesis investigates how well a neural architecture search can find competitive image classifiers on the CIFAR-10 data set with limited computational resources. Most work done on architecture search either uses vast computational resources or narrow and strongly informed space of possible solutions. LÄS MER

  7. 5. Revision of an artificial neural network enabling industrial sorting

    Master-uppsats, Uppsala universitet/Institutionen för teknikvetenskaper

    Författare :Henrik Malmgren; [2019]
    Nyckelord :artificial neural networks; machine learning; deep learning; connectionism; pattern recognition; machine learning; automation; image analysis; information technology; applied mathematics; mathematical optimization; information theory; mathematical statistics; mathematical models; stochastic models; probabilities; chance; approximations; algorithms; computer programs; computer software; signal processing; high performance computing; numerical methods; high technology industries; sustainable development; artificiella neurala nätverk; maskininlärning; djup maskininlärning; konnektionism; mönsterigenkänning; automatisering; bildanalys; informationsteknik; tillämpad matematik; optimering; informationsteori; statistisk inferens; matematiska modeller; stokastiska modeller; sannolikhetskalkyl; slumpen; approximationer; algoritmer; datorprogram; programvara; signalbehandling; högpresterande beräkningar; numeriska metoder; teknikutveckling; maskinindustri; högteknologisk industri; maskinhandel; skrothandel; bärkraftig utveckling;

    Sammanfattning : Convolutional artificial neural networks can be applied for image-based object classification to inform automated actions, such as handling of objects on a production line. The present thesis describes theoretical background for creating a classifier and explores the effects of introducing a set of relatively recent techniques to an existing ensemble of classifiers in use for an industrial sorting system. LÄS MER