Sökning: "Federerat lärande"
Visar resultat 1 - 5 av 8 uppsatser innehållade orden Federerat lärande.
1. Implementing a Network Optimized Federated Learning Method From the Ground up
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This bachelor thesis presents the implementation ofa simple fully connected neural network (FCNN) and federatedneural network with stochastic quantization from scratch andcompares their performance. Federated learning enables multipleparties to contribute to a machine learning model withoutsharing their sensitive data. LÄS MER
2. Software Fault Detection in Telecom Networks using Bi-level Federated Graph Neural Networks
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The increasing complexity of telecom networks, induced by the recent development of 5G, is a challenge for detecting faults in the telecom network. In addition to the structural complexity of telecommunication systems, data accessibility has become an issue both in terms of privacy and access cost. LÄS MER
3. Adversarial Attacks in Federated Learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Maskininlärning kräver olika utbildningsdatauppsättningar för att fungera bra. Att dela datauppsättningar är ofta en juridisk fråga och integritetsfråga mellan länder/företag. LÄS MER
4. Privacy leaks from deep linear networks : Information leak via shared gradients in federated learning systems
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The field of Artificial Intelligence (AI) has always faced two major challenges. The first is that data is kept scattered and cannot be collected for more efficiently use. The second is that data privacy and security need to be continuously strengthened. LÄS MER
5. Federated Learning for Market Surveillance
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The increasing complexity of trading strategies, when combined with machine learning models, forces market surveillance corporations to develop increasingly sophisticated methods for recognizing potential misuse. One strategy is to employ traders’ weapons against themselves, namely machine learning. LÄS MER