Sökning: "Decentralized network"
Visar resultat 1 - 5 av 160 uppsatser innehållade orden Decentralized network.
1. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : 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
2. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models
Master-uppsats, Umeå universitet/Institutionen för tillämpad fysik och elektronikSammanfattning : 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. En Social Nätverksanalys av ett Hackerforum
Kandidat-uppsats, Lunds universitet/Statsvetenskapliga institutionenSammanfattning : The spread and societal dependence on the internet has increased the threat posed by criminal hackers. While often thought of as lone wolfs, hackers often exist in communities and a widespread subculture. LÄS MER
4. Blockchains and Smart Contracts for Cryptocurrency : An Analysis of Their Functionality and Performance
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Smart contracts are self-executing electronic contracts. Amongst its deployed applications in the digital world is providing a decentralized and transparent method for executing transactions of cryptocurrencies on blockchains. LÄS MER
5. Multi-Agent Deep Reinforcement Learning in Warehouse Environments
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This report presents a deep reinforcement algorithm for multi-agent systems based on the classicalDeep Q-Learning algorithm. The method considers a decentralized approach to controlling theagents, by equipping each agent with its own neural network and replay memory. LÄS MER