Sökning: "Neural"

Visar resultat 16 - 20 av 3497 uppsatser innehållade ordet Neural.

  1. 16. AI-based image generation: The impact of fine-tuning on fake image detection

    Kandidat-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskap

    Författare :Nick Hagström; Anders Rydberg; [2024]
    Nyckelord :Fake image detection; LoRA; DreamBooth; Stable Diffusion; Image generation;

    Sammanfattning : Machine learning-based image generation models such as Stable Diffusion are now capable of generating synthetic images that are difficult to distinguish from real images, which gives rise to a number of legal and ethical concerns. As a potential measure of mitigation, it is possible to train neural networks to detect the digital artifacts present in the images synthesized by many generative models. LÄS MER

  3. 17. Stock Price Predictions for FAANG Companies Using Machine Learning Models

    Kandidat-uppsats, Lunds universitet/Statistiska institutionen

    Författare :Hugo Dahlquist; Fredrik Fourong; [2024]
    Nyckelord :Random Forest; Artificial Neural Networks; Stock prices; Predictions.; Mathematics and Statistics;

    Sammanfattning : The financial industry is one of the highest grossing sectors in the world as it is estimated to represent 24\% of the global economy. As most companies want their asset value to increase, it is of high interest to make good investments which will increase in either the short or long run. LÄS MER

  4. 18. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models

    Master-uppsats, Umeå universitet/Institutionen för tillämpad fysik och elektronik

    Författare :Sofia Leksell; [2024]
    Nyckelord :Federated Learning; Adversarial Attacks; Regression; Classification;

    Sammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving  a noticeable gap in FL research specifically for regression models. LÄS MER

  5. 19. Predicting inflow and infiltration to wastewater networks based on temperature measurements

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

    Författare :Martin Åsell; [2024]
    Nyckelord :Inflow and Infiltration; I I; CNN; Linear regression;

    Sammanfattning : Sewer pipelines are deteriorating due to aging and sub optimal material selections, leading to the infiltration of clean ground and rainfall water into the pipes. It is estimated that a significant portion (up to 40-50%) of the water entering wastewater treatment plants is actually clean infiltrated water. LÄS MER

  7. 20. Uncertainty Quantification in Deep Learning for Breast Cancer Classification in Point-of-Care Ultrasound Imaging

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Marisa Wodrich; [2024]
    Nyckelord :Uncertainty quantification; Deep learning; Breast cancer classification; Trustworthy AI; Point-of-care ultrasound; Mathematics and Statistics;

    Sammanfattning : Breast cancer is the most common type of cancer worldwide with an estimate of 2.3 million new cases in 2020, and the number one cause of cancer-related deaths in women. LÄS MER