Sökning: "IID"

Visar resultat 1 - 5 av 11 uppsatser innehållade ordet IID.

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

   Master-uppsats, Umeå universitet/Institutionen för datavetenskap

   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

3. 2. 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

4. 3. Federated Self-supervised Learning in Computer Vision

   Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Jonas Frankemölle; [2023]
   Nyckelord :;

   Sammanfattning : With an ever-increasing amount of available image data, self-supervised learning (SSL) circumvents the necessity for annotations in traditional supervised learning methods. SSL methods such as SimSiam have shown excellent results on popular benchmark datasets, even outperforming supervised methods. LÄS MER

5. 4. Personalized Federated Learning for mmWave Beam Prediction Using Non-IID Sub-6 GHz Channels

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

   Författare :Yuan Cheng; [2022]
   Nyckelord :Personalized Federated Learning; Millimeter wave; Beamforming; DeepMIMO; Non-IID; Personaliserad Federad Inlärning; Millimetervågor; Strålformning; DeepMIMO; Icke-IID;

   Sammanfattning : While it is difficult for base stations to estimate the millimeter wave (mmWave) channels and find the optimal mmWave beam for user equipments (UEs) quickly, the sub-6 GHz channels which are usually easier to obtain and more robust to blockages could be used to reduce the time before initial access and enhance the reliability of mmWave communication. Considering that the channel information is collected by a massive number of radio base stations and would be sensitive to privacy and security, Federated Learning (FL) is a match for this use case. LÄS MER

7. 5. Experiments of Federated Learning on Raspberry Pi Boards

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

   Författare :Simon Sondén; Farhad Madadzade; [2022]
   Nyckelord :Federated Learning; Raspberry Pi; FedAvg; Decentralized; Machine Learning; Convolutional Neural Network; PyTorch;

   Sammanfattning : In recent years, companies of all sizes have become increasingly dependent on customer user data and processing it using machine learning (ML) methods. These methods do, however, require the raw user data to be stored locally on a server or cloud service, raising privacy concerns. LÄS MER