Uboreshaji wa Stochastiki — SGD na Vigezo Vyake
Uboreshaji wa stochastiki ni familia ya mbinu za kurudia-rudia zinazopunguza utendaji kazi lengwa kwa kukokotoa miteremko kwenye sehemu ndogo za data zilizochaguliwa kwa nasibu — vikundi vidogo — badala ya kutumia data nzima mara moja. Njia hii, iliyoanzishwa na Robbins na Monro mwaka 1951 kama dhana ya kurekebisha stochastiki, ilikuja kuwa injini sanifu ya kufundisha mifumo mikubwa ya kujifunza kwa mashine kupitia vigezo kama vile SGD yenye kasi, AdaGrad, RMSProp, na Adam.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. Annals of Mathematical Statistics, 22(3), 400-407. DOI: 10.1214/aoms/1177729586 ↗
- Kingma, D.P. & Ba, J. (2015). Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (ICLR 2015). link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 1). Stochastic Optimization (SGD and Variants). ScholarGate. https://scholargate.app/sw/optimization/stochastic-optimization
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.
- Utaftaji wa BayesianUboreshaji↔ compare
- Mkakati wa Mageuzi (CMA-ES)Uboreshaji↔ compare
- Uboreshaji ImaraUboreshaji↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →