Sökning: "associative networks"

Visar resultat 1 - 5 av 11 uppsatser innehållade orden associative networks.

  1. 1. Sequence Disambiguation in a Brain-Like Recurrent Neural Network with Local Associative Learning

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

    Författare :Ivan Pavlovich Zelenin; Mina Beigi Boroujeni; [2020]
    Nyckelord :;

    Sammanfattning : The learning of sequences is a fundamental ability of biological networks. While there are many artificial networks that are able to successfully learn sequences, it is of particular interest to study networks that attempt to do so in a manner similar to how it is done by a human brain. LÄS MER

  3. 2. Semi-Supervised Domain Adaptation for Pick Classification in Pick and Place Machines

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

    Författare :Mitra Strandberg; [2019]
    Nyckelord :;

    Sammanfattning : Pick and Place (PnP) machines collect and use large amounts of image data of Printed Circuit Board (PCB) components. The data is used to train automated image analysis methods to improve the decisions in the mounting process. Previous work with Neural Networks has shown promising results in the classification of the component status. LÄS MER

  4. 3. The (perhaps) causal brain : A comparison of attractor neural networks usingtemporally symmetric and antisymmetric synapticrules

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)

    Författare :Leo Lindén; [2018]
    Nyckelord :;

    Sammanfattning : The associative memory of the brain is thought to be well modelled by attractorneural networks. A sort of artificial neural network that may store memories and has the ability to associate them with distorted input. LÄS MER

  5. 4. Multi-person Pose Estimation in Soccer Videos with Convolutional Neural Networks

    Master-uppsats, Linköpings universitet/Matematisk statistik; Linköpings universitet/Tekniska fakulteten

    Författare :Axel Skyttner; [2018]
    Nyckelord :Deep Learning; Pose Estimation; Sport Analysis;

    Sammanfattning : Pose estimation is the problem of detecting poses of people in images, multiperson pose estimation is the problem of detecting poses of multiple persons in images. This thesis investigates multi-person pose estimation by applying the associative embedding method on images from soccer videos. LÄS MER

  7. 5. Weight Matrix Adaptation for increased Memory Storage Capacity in a Spiking Hopfield Network

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)

    Författare :Ciwan Ceylan; Albin Sunesson; [2015]
    Nyckelord :;

    Sammanfattning : Lagringskapaciteten i ett litet spiking Hopfieldnätverk undersöks med hjälp av två parametrar som styr resistansen och inhibitionen hos de synaptiska kopplingarna. Det är motiverat av möjligheten att skapa större associativa nätverk från små nätverkskluster. LÄS MER