Thesis icon

Thesis

Multi-agent learning

Abstract:

Machine learning models are often trained on data stored across multiple computers connected by a network. Due to network stability, it is then often infeasible for a single central-hub computer to process and disseminate information. A solution to overcome this bottleneck is to consider a decentralised network akin to peer-to-peer and ad-hoc wireless networks. Namely, computers communicate to a sub-set of other computers at a time, with information then naturally propagating through the n...

Expand abstract

Actions


Access Document


Files:

Authors


More by this author
Division:
MPLS
Department:
Statistics
Role:
Author

Contributors

Role:
Contributor
Role:
Contributor
Role:
Contributor
Type of award:
DPhil
Level of award:
Doctoral
Awarding institution:
University of Oxford

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP