RNNi iliyofunzwa kwa udhaifu
RNN iliyofunzwa kwa udhaifu huendesha mtandao wa neva unaojirudia kwenye milururuko ambao lebo zake hutoka kwa vyanzo visivyo kamili — sheria za msaada, usimamizi wa mbali, utoaji wa maoni kutoka kwa umati, au mifumo ya lebo ya uzalishaji — badala ya kuandika kwa gharama kubwa na wataalam. Hii huwaruhusu watafiti kutumia makusanyo makubwa yasiyo na lebo kwa ajili ya kazi za mlururuko kama vile uainishaji wa maandishi, utambuzi wa jina la kipekee, au utabiri wa mfululizo wa muda wakati data iliyoandikwa kikamilifu ni adimu au ya gharama.
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
- Ratner, A., De Sa, C., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗
- Zhou, Z.-H. (2018). A brief introduction to weakly supervised learning. National Science Review, 5(1), 44–53. DOI: 10.1093/nsr/nwx106 ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Weakly Supervised Recurrent Neural Network. ScholarGate. https://scholargate.app/sw/deep-learning/weakly-supervised-recurrent-neural-network
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.
- Gated Recurrent Unit (GRU)Ujifunzaji wa Kina↔ compare
- Long Short-Term Memory (LSTM)Ujifunzaji wa Kina↔ compare
- Mtandao wa Nyuro UnaojirudiaUjifunzaji wa Kina↔ compare
- LSTM iliyo na Usimamizi dhaifuUjifunzaji wa Kina↔ compare
- Transformer ya Usimamizi dhaifuUjifunzaji wa Kina↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →