Sökning: "Stochastic process"

Visar resultat 1 - 5 av 133 uppsatser innehållade orden Stochastic process.

  1. 1. 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

  2. 2. Network Drone Control using Deep Reinforcement Learning

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

    Författare :Alex Hermansson Grobgeld; [2020]
    Nyckelord :;

    Sammanfattning : In this work, a reinforcement learning approach is adopted to control a drone in a cellular network. The goal is to find paths between arbitrary locations such that low radio quality areas, defined with respect to signal-to-interference-plus-noise-ratio, are avoided with the cost of longer flight paths. LÄS MER

  3. 3. Sequence Prediction for Identifying User Equipment Patterns in Mobile Networks

    Master-uppsats, KTH/Matematisk statistik

    Författare :Theoharis Charitidis; [2020]
    Nyckelord :Markov chain; mobile networks; user equipment; machine learning; statistics; sequence prediction; stochastic process; Maskininlärning; mobila nätverk; statistik; markovkedjor; all k order markov; stokastisk process; sekvensprediktering;

    Sammanfattning : With an increasing demand for bandwidth and lower latency in mobile communication networks it becomes gradually more important to improve current mobile network management solutions using available network data. To improve the network management it can for instance be of interest to infer future available bandwidth to the end user of the network. LÄS MER

  4. 4. Simulation and statistical methods for stochastic differental equations

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Christian Källgren; [2019-12-16]
    Nyckelord :;

    Sammanfattning : We look at numerical methods for simulation of stochastic differential equationsexhibiting volatility induced stationarity. This is a property of the process whichmeans that the stationary behaviour is mostly imposed by how volatile the processis. The property creates issues in simulation and hence also in statistical methods. LÄS MER

  5. 5. Simulation and statistical methods for stochastic differental equations

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Christian Källgren; [2019-12-11]
    Nyckelord :;

    Sammanfattning : We look at numerical methods for simulation of stochastic differential equationsexhibiting volatility induced stationarity. This is a property of the process whichmeans that the stationary behaviour is mostly imposed by how volatile the processis. The property creates issues in simulation and hence also in statistical methods. LÄS MER