Sökning: "Leaky"

Visar resultat 1 - 5 av 50 uppsatser innehållade ordet Leaky.

  1. 1. Comparing energy efficiency of Leaky integrate-and-fire and Spike response neuron models in Spiking Neural Networks

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

    Författare :Majd Dawli; Imran Bahed Diva; [2023]
    Nyckelord :;

    Sammanfattning : Spiking Neural Networks (SNNs) are a type of neural network that is designed to mimic the way neurons function in our brains. While there have been notable advancements in developing SNNs, energy consumption hasn't been studied to the same extent. This gets especially relevant with steadily increasing network sizes. LÄS MER

  3. 2. Molecular characterization of vascular malformations using single-cell RNA sequencing and immunohistological analysis

    Master-uppsats, Uppsala universitet/Institutionen för biologisk grundutbildning

    Författare :Amanda Norrén; [2023]
    Nyckelord :;

    Sammanfattning : CCM is a human disease in which vascular malformations develop in the central nervous system, predominantly in the brain. The malformations which can measure up to several centimeters in size are dilated and leaky vessels, with unstable cellular junctions and thin vessel walls. LÄS MER

  4. 3. Exploring Normalizing Flow Modifications for Improved Model Expressivity

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

    Författare :Marcel Juschak; [2023]
    Nyckelord :Normalizing Flows; Motion Synthesis; Invertible Neural Networks; Glow; MoGlow; Maximum Likelihood Estimation; Generative models; normaliserande flöden; rörelsesyntes; inverterbara neurala nätverk; Glow; MoGlow; maximum likelihood-skattning generativa modeller;

    Sammanfattning : Normalizing flows represent a class of generative models that exhibit a number of attractive properties, but do not always achieve state-of-the-art performance when it comes to perceived naturalness of generated samples. To improve the quality of generated samples, this thesis examines methods to enhance the expressivity of discrete-time normalizing flow models and thus their ability to capture different aspects of the data. LÄS MER

  5. 4. Blind Acoustic Feedback Cancellation for an AUV

    Master-uppsats, Linköpings universitet/Reglerteknik

    Författare :Hampus Frick; [2023]
    Nyckelord :acoustical feedback; adaptive filter; least leaky mean square; Kalman; blind source separation; independent component analysis; complex independent component analysis; degenerative unmixing estimation technique; convolutive mixture;

    Sammanfattning : SAAB has developed an autonomous underwater vehicle that can mimic a conventional submarine for military fleets to exercise anti-submarine warfare. The AUV actively emits amplified versions of received sonar pulses to create the illusion of being a larger object. LÄS MER

  7. 5. Fractional proportional-integrative-derivative controller : Design, analysis and applications to DC motor and single neuron spiking

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Institutionen för elektroteknik

    Författare :Hassan Soltani; [2023]
    Nyckelord :Fractional; FPID;

    Sammanfattning : This thesis aims to explore and compare the performance of fractional proportional-integrative-derivative controllers in the DC motor system and the fractional leaky integrate and fire (FLIF) model for neuron spike signals. The objective is to determine whether FPID controllers exhibit superior performance and significant improvements in control compared to PID controllers. LÄS MER