Caadiyan Kediska Socodka

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay hantida xisaabeed ee ay tahay in isbeddel kasta ee socodka caadiga ah uu yeesho?
   • Waa inay noqotaa khariidad random ah, oo aan leexleexad lahayn
   • Waa inuu noqdaa mid aan leexan karin (bijective) oo la kala saari karo
   • Waa inay hoos u dhigtaa cabbirka tallaabo kasta
   • Waa in uu ahaado miis si gaar ah loo eegayo
2. Qaabkee u ogolaanaya in socodka caadiga ah uu xisaabiyo suurtagalnimada saxda ah?
   • Shaqada softmax
   • Isla'egta Bellman
   • Xeerka Bayes ayaa lagu dabaqay saadka
   • Qaaciddada isbeddelka-isbeddelka ah iyadoo la adeegsanayo go'aamiye Yacquub
3. Waa maxay sababta qaab-dhismeedyada socodka sida RealNVP iyo Glow u isticmaalaan lakabyo isku-xidhan?
   • Si loo sameeyo saddex xagalka reer Yacquub si go'aamiyeheedu u jaban yahay in la xisaabiyo
   • Si aad moodelka uga dhigto mid aan leexleexan karin
   • Si meesha looga saaro baahida qaybinta salka
   • Si loogu beddelo moodalka GAN
4. What does a tractable normalizing flow provide that an ordinary GAN generator generally does not?
   • A guarantee of perfect anomaly detection
   • A guarantee of faster sampling than every GAN
   • An explicitly evaluable model density through change of variables
   • A non-invertible mapping with no base distribution
5. How should a team use normalizing-flow likelihoods for anomaly detection?
   • Assume every high-likelihood input is familiar
   • Treat density as the probability mass of a single point
   • Skip checking real anomaly labels
   • Validate them as a signal against relevant in-distribution and anomalous examples
6. Waa kuwee farsamada casriga ah, ee loo isticmaalo nidaamyada sida Stable Diffusion 3, oo ka soo baxay fikradaha socodka joogtada ah?
   • Dib u faafinta waqtiga
   • Isbarbardhigga socodka (barashada goob xawaare ah oo qaylada u qaada xogta)
   • Calaamadaynta
   • Baadhitaanka Beam
7. A one-dimensional flow inverse is z = x / 2. What log-Jacobian term appears in log p(x)?
   • log(2)
   • The parameter count of the network
   • log(1/2)
   • No term because the inverse is linear
8. Why must a normalizing flow account for stretching or shrinking volume?
   • A transformed region’s density must reflect the changed volume
   • The transformation must lose half its dimensions
   • Every output point must have probability mass one
   • The base distribution must be discarded after training