Kediska Qaababka Dhalmada Ku Salaysan Dhibcaha

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay dhab ahaan 'dhibcaha' ay moodooyinkani bartaan?
   • Dareenka cufnaanta ixtimaalka log-ka ee ku saabsan gelinta
   • Qiimaynta tayada laga bilaabo 0 ilaa 100 sawir kasta
   • Tirada waayihii tababarka ee la dhammeeyay
   • Summada kala soocidda barta xogta
2. Waa maxay sababta moodooyinka dhibcaha ku salaysan loogu tababaray xogta lagu kharribmay buuqa miisaanyo badan?
   • Si sawirada looga dhigo kuwo farshaxan
   • Sababtoo ah dhibcuhu way adagtahay in la qiyaaso halka xogta nadiifka ah ay ku yar tahay, iyo qaylada ayaa buuxisa gobolladaas
   • Si loo yareeyo cabbirka faylka xogta
   • Sababtoo ah qaylada ayaa dedejisa GPU-ga
3. Nidaamkee muunada ayaa moodooyinka ku salaysan dhibcaha hore adeegsadeen si ay u soo saaraan xogta?
   • Hoos ugu dhaadhacaya pixels-yada oo u socda muuqaal bartilmaameed go'an
   • Isku dhufashada hal matrix
   • Dhaqdhaqaaqa Langevin - ku talaabsashada dhibcaha adigoo ku daraya buuq
   • Goynta iyo rogrogashada random
4. Waa maxay xidhiidhka weyn ee 2021 buundada-SDE warqad aasaasay?
   • Taasi GAN-yadu had iyo jeer way ka fiican yihiin fidinta
   • Shabakadaha neerfaha ma samayn karaan sawirro
   • Moodooyinka dhibcahaasi waxay ku shaqeeyaan kaliya laba cabbir
   • Qaababka fidinta iyo moodooyinka ku salaysan dhibcaha ayaa ah laba aragtiyood oo isku mid ah habka SDE ee joogtada ah
5. Sidee buu saadaasha sawaxanku ula xidhiidhaa saadaalinta dhibcaha diidmada isbarbardhigga dhibcaha?
   • The conditional denoising-score target is −ε/σ for standardized Gaussian noise; the model estimates the noisy-data score
   • Noise prediction and score estimation are unrelated
   • Saadaasha qaylada waa wax aan macquul ahayn
   • Dhibcuhu had iyo jeer waa eber xogta buuqa badan
6. Maxay go'aaminta 'qulqulka itimaalka ODE' u suurtagelinayaa in muunad saafiga ah ee stochastic aysan si fudud u bixin?
   • Isticmaalka korantada GPU sare
   • Xisaabinta suurtogalka ah ee saxda ah iyo dariiq muunad go'aamineed
   • Si toos ah u calaamadinta xogta
   • Ka saarida baahida shabakad kasta oo neerfaha ah
7. In score-based generation, what does the reverse-time SDE do?
   • It converts image labels into captions
   • It adds noise to an already generated output only
   • It transforms a prior noise distribution back toward the data distribution
   • It estimates the class label of each pixel
8. In a score-based MRI reconstruction method, how can a learned image prior help recover an undersampled scan?
   • Use the prior alone and ignore measured k-space data
   • Combine the learned score prior with the measurement constraint during posterior sampling
   • Replace all measurements with random noise
   • Treat the score as a diagnosis of the patient