quiz bu lëkkale ak tegtal · Dëgër Niveau

Quiz buy jaar yoon

Jàngaleel coppite yi am ci debit buñ mëna soppi, coppite ci densité variable yi, ak jubbanti Jacobian, boole ci yam ci gis anomalie yi lalu ci probabilite.

Yooni njiit yu jëm ciNormalise ay debit
Laaj 1 de 8

Ban màndarga math la coppite bu nekk ci flow buy normalise wara am?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Ban màndarga math la coppite bu nekk ci flow buy normalise wara am?
    • Dafa wara nekk kàrt buñ mëna soppiku, buñu dul soppi
    • Dafa wara nekk luñu mëna soppi (bijektif) ak luñu mëna wuutale
    • Dafa wara wàññi dimension ci jéego bu nekk
    • Dafa wara nekk tablo seetlu bu wuute
  2. Ban formul mooy tax ñu mëna xayma limu mëna am ci anam wu jaar yoon?
    • Fonction softmax bi
    • Equation Bellman
    • Regle bu Bayes bi ñuy jëfandikoo ci logits yi
    • Formul coppite-ci-variable yi jëfandikoo determinant jacobian
  3. Lan moo waral architecture yu melni RealNVP ak Glow di jëfandikoo ay couplage?
    • Defar benn ñatti kaar bu jacobian, kon determinant bi yomb naa xayma
    • Def model bi mënul soppiku
    • Ngir dindi soxla séddale bu njëkk
    • Ngir soppi xeetu 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. Ban pexem jamono lañuy jëfandikoo ci sistem yu melni Stable Diffusion 3, mu juddoo ci xalaat yuy wéy di daw?
    • Backpropagation ci diir bi
    • Flow matching (jàng benn gaawaay buy yóbbu bruit ci done yi)
    • Tokenisasioŋ
    • Seetug limyéer
  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