Sökning: "Convolutional Neural Networks"

Visar resultat 1 - 5 av 301 uppsatser innehållade orden Convolutional Neural Networks.

  1. 1. Hand Gesture Classification using Millimeter Wave Pulsed Radar

    Master-uppsats, Lunds universitet/Matematisk statistik

    Författare :Eda Dagasan; [2020]
    Nyckelord :Hand Gesture Classification; Millimeter Wave Radar; Statistical Signal Processing; Time-Frequency Analysis; Room Impulse Response Estimation; Sparse Dictionary Learning; Classification; Supervised Learning; Convolutional Neural Networks; k-Nearest Neighbor; Mathematics and Statistics;

    Sammanfattning : Millimeter wave pulsed radar has found many applications, among them hand gesture sensing, which this work has as purpose. This application has already shown good potential, [1], and here in this work robustness aspects are taken into account. LÄS MER

  3. 2. A Study of the Loss Landscape and Metastability in Graph Convolutional Neural Networks

    Master-uppsats, KTH/Matematisk statistik

    Författare :Sofia Larsson; [2020]
    Nyckelord :Graph neural networks; Graph convolutional neural networks; Loss landscape; Gradient descent; Stochastic gradient descent; Stochastic gradient Langevin dynamics; Grafneurala nätverk; grafiska faltningsnätverk; lösningslandskap; gradientmetoder; stokastiska gradientmetoder; stokastisk gradient Langevin dynamik;

    Sammanfattning : Many novel graph neural network models have reported an impressive performance on benchmark dataset, but the theory behind these networks is still being developed. In this thesis, we study the trajectory of Gradient descent (GD) and Stochastic gradient descent (SGD) in the loss landscape of Graph neural networks by replicating Xing et al. LÄS MER

  4. 3. Instance Segmentation of Buildings in Satellite Images

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Karin Fritz; [2020]
    Nyckelord :cnn; convolutional neural networks; instance segmentation; semantic segmentation;

    Sammanfattning : When creating a photo realistic 3D model of the world using satellite imagery, image classification is an important part of the process. In this thesis the specificpart of automated building extraction is investigated. LÄS MER

  5. 4. Hyperparameter Optimization for Convolutional Neural Networks

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

    Författare :Clément Gousseau; [2020]
    Nyckelord :;

    Sammanfattning : Training algorithms for artificial neural networks depend on parameters called the hyperparameters. They can have a strong influence on the trained model but are often chosen manually with trial and error experiments. LÄS MER

  7. 5. Depth Estimation from Images using Dense Camera-Lidar Correspondences and Deep Learning

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

    Författare :Ajinkya Khoche; [2020]
    Nyckelord :;

    Sammanfattning : Depth estimation from 2D images is a fundamental problem in Computer Vision, and is increasingly becoming an important topic for Autonomous Driving. A lot of research is driven by innovations in Convolutional Neural Networks, which efficiently encode low as well as high level image features and are able to fuse them to find accurate pixel correspondences and learn the scale of the objects. LÄS MER