Avancerad sökning

Hittade 1 uppsats som matchar ovanstående sökkriterier.

1. 1. Differentially Private Federated Learning

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

   Författare :Nikolaos Tatarakis; [2019]
   Nyckelord :;

   Sammanfattning : Federated Learning is a way of training neural network models in a decentralized manner; It utilizes several participating devices (that hold the same model architecture) to learn, independently, a model on their local data partition. These local models are then aggregated (in parameter domain), achieving equivalent performance as if the model was trained centrally. LÄS MER