ScholarGate
Msaidizi
Machine learning

Kushuka kwa Gradient kwa Bahati Nasibu (SGD)

Kushuka kwa Gradient kwa Bahati Nasibu (SGD) ni algorithm ya kuendeleza hatua ya kwanza, iliyoandaliwa kutoka mfumo wa makadirio ya bahati nasibu ulioanzishwa na Robbins na Monro mnamo 1951, ambayo hupunguza kazi lengwa kwa kusasisha vigezo vya mfumo kwa kutumia gradient iliyohesabiwa kwa mfano mmoja wa mafunzo uliochaguliwa kwa nasibu (au kundi dogo) katika kila hatua. Ni injini kuu ya kuendeleza nyuma ya akili bandia ya kisasa na akili ya kina, ikiwezesha mafunzo ya mifumo kwenye seti za data kubwa sana kutoshea kwenye kumbukumbu.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

The neighbourhood of related methods — select a node to explore.

Vyanzo

  1. Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3), 400–407. DOI: 10.1214/aoms/1177729586
  2. Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning (Ch. 8). MIT Press. ISBN: 978-0-262-03561-3

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Stochastic Gradient Descent (SGD) Optimization Algorithm. ScholarGate. https://scholargate.app/sw/machine-learning/stochastic-gradient-descent

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.

Compare side by side

Imerejelewa na

ScholarGateStochastic Gradient Descent (Stochastic Gradient Descent (SGD) Optimization Algorithm). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/machine-learning/stochastic-gradient-descent · Seti ya data: https://doi.org/10.5281/zenodo.20539026