Mifumo ya Kawaida ya Mtiririko
Mifumo ya kawaida ya mtiririko ni kundi la mifumo jenereta inayojifunza usambazaji changamano wa uwezekano kwa kutumia mfuatano wa mabadiliko yanayoweza kugeuzwa na kutofautishwa kwenye usambazaji rahisi wa msingi kama vile Gaussian sanifu. Ilianzishwa na Rezende na Mohamed (2015) katika muktadha wa hitimisho la kibadala, huwezesha hesabu kamili ya uwezekano na sampuli yenye ufanisi, na kuifanya kuwa mbadala wa kimsingi kwa VAEs na GANs kwa makadirio ya msongamano na kazi za uzalishaji.
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
- Rezende, D. J., & Mohamed, S. (2015). Variational inference with normalizing flows. International Conference on Machine Learning (ICML), 1530–1538. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 2). Normalizing Flows. ScholarGate. https://scholargate.app/sw/deep-learning/normalizing-flows
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.
- Mfumo wa UenezajiUjifunzaji wa Kina↔ compare
- Variational AutoencoderUjifunzaji wa Kina↔ compare
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →