Sökning: "Syntetiska nätverk"

Visar resultat 1 - 5 av 41 uppsatser innehållade orden Syntetiska nätverk.

  1. 1. Evaluating the Viability of Synthetic Pre-training Data for Face Recognition Using a CNN-Based Multiclass Classifier

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

    Författare :Lars Bergström; Dag Hjelm; [2023]
    Nyckelord :;

    Sammanfattning : Today, face recognition is becoming increasingly accurate and faster with deep learning methods such as convolutional neural networks (CNNs), and is now widely used in areas such as security and entertainment. Typically, these CNNs are trained using real-face datasets like CASIA-WebFace, which was put together using web-crawling of IMDB. LÄS MER

  3. 2. 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

  4. 3. Synthesizing of brain MRE wave data

    Master-uppsats, KTH/Medicinsk avbildning

    Författare :Maryia Yuliuhina; [2023]
    Nyckelord :MR elastography; brain MRE; synthetic data; computational modeling; shear wave elastography; MR-elastografi; hjärn MRE; syntetiska data; beräkningsmodellering; skjuvvåg elastografi;

    Sammanfattning : Magnetic resonance elastography (MRE) is an imaging technique that allows for non-invasive access to the physical properties of body tissues. MRE has great potential, but it is difficult to conduct research due to the time-consuming estimation of stiffness maps, which could be speeded up by using neural network. LÄS MER

  5. 4. Unsupervised Domain Adaptation for Regressive Annotation : Using Domain-Adversarial Training on Eye Image Data for Pupil Detection

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

    Författare :Erik Zetterström; [2023]
    Nyckelord :Neural networks; Deep learning; Convolutional neural networks; Transfer learning; Domain adaptation; Unsupervised training; Adversarial training; Keypoint detection; Regression; Neurala nätverk; Djupinlärning; Faltningsnätverk; Överförningsinlärning; Domänadaptering; Oövervakad inlärning; Motstående träning; Nyckelpunktsdetektion; Regression;

    Sammanfattning : Machine learning has seen a rapid progress the last couple of decades, with more and more powerful neural network models continuously being presented. These neural networks require large amounts of data to train them. LÄS MER

  7. 5. Credit Card Transaction Fraud Detection Using Neural Network Classifiers

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

    Författare :Ehsan Nazeriha; [2023]
    Nyckelord :GAN; Deep Learning; Variational Autoencoder; Anomaly Detection; SMOTE; GAN; Djupinlärning; Variational Autoencoder; Anomali detektering; SMOTE;

    Sammanfattning : With increasing usage of credit card payments, credit card fraud has also been increasing. Therefore a fast and accurate fraud detection system is vital for the banks. To solve the problem of fraud detection, different machine learning classifiers have been designed and trained on a credit card transaction dataset. LÄS MER