quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz Reseau Adversaire Generatif

Xoolaat cër yi defarkat yi ak tànneef yi, duggal GAN ​​yu njëkk yi, feedback adversarial, daanu mode, cosaani taarix, dayo, ak kondisione.

Yooni njiit yu jëm ciReseau adversaire yu defar
Laaj 1 de 8

Lan mooy ñaari reso yiy joŋante ci benn GAN?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan mooy ñaari reso yiy joŋante ci benn GAN?
    • Encodeur ak decodeur
    • Jàngatkat ak bindkat
    • Ñaari kopi yu nuróo yuy déggoo saa yu nekk
    • Generateur buy defar ay faux ak discriminateur bu leen di àtte
  2. In the original unconditional GAN formulation, what input does the generator transform into a sample?
    • A guaranteed copy of a finished real image
    • Sampled latent noise
    • The discriminator's parameter file
    • A fixed human-written answer key
  3. What adversarial learning signal can reach a GAN generator through its discriminator?
    • Gradients of the generator objective with respect to its parameters
    • A rule that every generated image is correct
    • A prohibition against all conditional image inputs
    • A copy of every discriminator weight as the output image
  4. Luy 'dagg mode' ci GAN?
    • Discriminateur bi dafay efaase bépp done
    • Reseau bi daa jeex ci mémoire bi
    • Generatër bi du defar ay sorti yu bari yuy baamtu, du ay sorti yu bari
    • Dayo nataal bi dafay yokk ci saasi ñaari yoon
  5. Which researchers introduced the GAN framework in the 2014 paper?
    • Alan Turing alone in 1950
    • Ian Goodfellow ak ay naataangoom
    • Geoffrey Hinton alone in 2006
    • Yann LeCun alone in 1998
  6. How can a conventional feed-forward GAN generator produce one sample after training?
    • By requiring exactly a thousand discriminator updates at inference
    • By retrieving an unchanged target image in every case
    • Without evaluating any learned computation
    • With one forward evaluation of the generator
  7. At the ideal original GAN equilibrium where generated and real distributions match, what probability does the optimal discriminator assign to an example being real?
    • Zero for every example
    • One for every example
    • One-half
    • A probability greater than one
  8. In the conditional GAN formulation, where can a class label or other condition be supplied?
    • To both the generator and the discriminator
    • Only to an unrelated output filename
    • To neither network by definition
    • Only after all training and generation have finished