Sökning: "Gossip learning"

Visar resultat 1 - 5 av 6 uppsatser innehållade orden Gossip learning.

1. 1. ”DET KAN TILL OCH MED FÖRSTÖRA LIV”. En kritisk diskursanalys om nyhetsmediernas framställning av sociala medier-kunnighet i samband med skvallerkonton

   Kandidat-uppsats, Göteborgs universitet/Institutionen för journalistik, medier och kommunikation

   Författare :Mikaela Pijpers; [2024-03-11]
   Nyckelord :Mediekunnighet; sociala medier-kunnighet; social media literacy; mediediskurs; skvallerkonto;

   Sammanfattning : This study deals with social media literacy by examining how media discuss the so-called rumor accounts on popular networking sites. This topic is relevant since this phenomenon first gained a lot of media attention back in 2012, with “Instagram-upploppen” making major headlines. LÄS MER

3. 2. Comparing decentralized learning to Federated Learning when training Deep Neural Networks under churn

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

   Författare :Johan Vikström; [2021]
   Nyckelord :Peer- to- Peer; Decentralized Machine Learning; Federated Learning; Gossip Learning; Long Short- Term Memory; Convolutional Neural Network; Peer- to- peer; Decentraliserad Maskininlärning; Federated learning; Gossip learning; Lång korttidsminne;

   Sammanfattning : Decentralized Machine Learning could address some problematic facets with Federated Learning. There is no central server acting as an arbiter of whom or what may benefit from Machine Learning models created by the vast amount of data becoming available in recent years. LÄS MER

4. 3. Distributed Robust Learning

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

   Författare :Akhil Yerrapragada; [2021]
   Nyckelord :Byzantine resilient decentralized training; Gradient aggregation rules; α; f Byzantine resilience; Fault tolerance; Ring all-reduce.; Byzantinsk motståndskraftig decentraliserad träning; Gradientaggregeringsregler; α; f Byzantinsk motståndskraft; Feltolerans; Ring allreducera.;

   Sammanfattning : Accuracy obtained when training deep learning models with large amounts of data is high, however, training a model with such huge amounts of data on a single node is not feasible due to various reasons. For example, it might not be possible to fit the entire data set in the memory of a single node, training times can significantly increase since the dataset is huge. LÄS MER

5. 4. Decentralized Large-Scale Natural Language Processing Using Gossip Learning

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

   Författare :Abdul Aziz Alkathiri; [2020]
   Nyckelord :gossip learning; decentralized machine learning; distributed machine learning; NLP; Word2Vec; data privacy; skvallerinlärning; decentraliserad maskininlärning; distribuerad maskininlärning; naturlig språkbehandling; Word2Vec; dataintegritet;

   Sammanfattning : The field of Natural Language Processing in machine learning has seen rising popularity and use in recent years. The nature of Natural Language Processing, which deals with natural human language and computers, has led to the research and development of many algorithms that produce word embeddings. LÄS MER

7. 5. The Moral of the Story: Growing up in A Gossip’s Story, Sense and Sensibility, Jane Eyre and Little Women

   Kandidat-uppsats, Lunds universitet/Engelska

   Författare :Rebecca Ferding; [2020]
   Nyckelord :bildungsroman; novels of development; jane austen; jane west; louisa may alcott; charlotte brontë; Languages and Literatures;

   Sammanfattning : In nineteenth-century literature, the heroine is often a young woman growing up and learning about the restrictions of gender and society. If she learns from the mistakes she is inevitably going to make, she may be rewarded … with a suitor? How does this correlate, who are the heroines and who are the suitors? This essay aims to answer these questions, along with evaluating parents in literature and assessing their relationships with their daughters to see if that has any effects on their marital outcomes. LÄS MER