Federated Learning
Federated Learning ni mfumo wa kujifunza mashine uliotawanywa ambao ulianzishwa na McMahan et al. mwaka 2017 ambapo modeli ya kimataifa hufunzwa kwa ushirikiano katika kompyuta nyingi zilizotawanywa — kama vile vifaa vya mkononi au mifumo ya hospitali — bila kuhamisha data ghafi kamwe kwenye seva kuu. Kila mshiriki huhesabu masasisho ya modeli ndani ya nchi kwa kutumia data yake ya faragha; ni masasisho hayo tu, si data ya msingi, yanayowasiliana na kuunganishwa na seva ili kuboresha modeli iliyoshirikiwa.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
+4 more
Vyanzo
- McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Artificial Intelligence and Statistics, 1273–1282. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 2). Federated Learning. ScholarGate. https://scholargate.app/sw/privacy/federated-learning
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Faragha TofautiFaragha↔ compare
- Ufumbuzi wa MaarifaUjifunzaji wa Kina↔ compare
- Kushuka kwa Gradient kwa Bahati Nasibu (SGD)Ujifunzaji wa Mashine↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →