Kediska Jadwalka Heerka Waxbarashada

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay ujeedada marxaladda 'kulanka' ee jadwalka heerka waxbarashada?
   • Si aad u bilawdo qiime yar oo aad kor ugu qaaddo, adigoo iska ilaalinaya xasiloonidarada ka imanaysa jaranjarada hore ee buuqa
   • Si saxnaanta kama dambaysta ah loo yareeyo
   • Si aad uga gudubto xogta dufcadaha ugu horreeya
   • Si aad u qaboojiso dhammaan miisaanka bilowga
2. Jadwalkee ayaa si habsami leh u raacaya qalooca cosine-ka bar ee hoos ugu socda heerka ugu hooseeya?
   • Jadwalka joogtada ah
   • Cosine annealing
   • Jadwalka random
   • Korodhka toosan
3. Maxaa dhacaya haddii heerka waxbarashadu aad u sarreeyo?
   • Tabobarku isla markaaba wuxuu isu keenaa saxnaan qumman
   • Habkani si tartiib tartiib ah ayuu u tabobarayaa laakiin had iyo jeer wuu guulaystaa
   • Khasaaruhu wuu kala duwanaan karaa ama wuu gilgili karaa intii uu yarayn lahaa
   • Wax isbedel ah ma jiraan; heerka wax saameyn ah kuma laha
4. Muxuu suusku ku sameeyaa heerka waxbarashada?
   • Waxay u kordhisaa si toos ah dufcad kasta
   • Waxay u dhigtaa mid joogto ah
   • U dejiyaa si aan kala sooc lahayn tillaabo kasta
   • Waxay ku riddaa qodob go'an xilliyadii hore loo sii qeexay
5. What does a warm restart do to a learning-rate schedule?
   • It raises the learning rate again to begin another schedule cycle
   • It resets the model parameters to random values
   • It permanently fixes the learning rate at zero
   • It deletes the optimizer’s moment estimates
6. In Goyal et al.’s large-minibatch ImageNet setup, what did their warmup scheme address?
   • It removed the need for a validation set
   • It eased early optimization difficulties after the learning-rate scale increased with batch size
   • It changed the model architecture after each epoch
   • It converted the learning-rate curve into a cosine wave
7. In the cosine formula, what does T denote?
   • The number of model layers
   • Cabbirka dufcadda
   • The schedule horizon or total number of steps used for the decay
   • The optimizer’s momentum coefficient
8. If the cosine schedule uses lr_min greater than zero, where does the rate approach at the end of the horizon?
   • Exactly zero regardless of lr_min
   • The original warmup starting rate
   • An unbounded value
   • The specified minimum learning rate