Guide-yakabatana mibvunzo · Zvakaoma Nhanho

Normalizing Inoyerera Quiz

Dzidzira invertible kuyerera shanduko, shanduko-ye-variables densities, uye Jacobian gadziriso, kusanganisira miganhu yekugona-kwakavakirwa anomaly yekuona.

Nzira dzekutungamira dzinoenderanaNormalizing Flows
Mubvunzo 1 ye 8

Ndeupi pfuma yemasvomhu inofanira kuve neshanduko yese mukuyerera kweyakajairika?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Ndeupi pfuma yemasvomhu inofanira kuve neshanduko yese mukuyerera kweyakajairika?
    • Inofanira kunge iri mepu isina kurongeka, isingachinjiki
    • Inofanira kuva invertible (bijective) uye inosiyanisa
    • Inofanira kuderedza chiyero padanho rega rega
    • Inofanira kunge iri tafura yekutarisa yakasarudzika
  2. Ndeipi fomula inobvumira kuyerera kuyerera kuverengera mikana chaiyo?
    • The softmax basa
    • Iyo Bellman equation
    • Mutemo weBayes unoshandiswa kune marogi
    • Shanduko-ye-inosiyana-siyana formula uchishandisa Jacobian determinant
  3. Sei kuyerera zvivakwa seRealNVP uye Glow vachishandisa machira ekubatanidza?
    • Kugadzira iyo Jacobian triangular saka chirevo chayo chakachipa kuverengera
    • Kuita kuti modhi irege invertible
    • Kubvisa kudiwa kwekugovera kwekutanga
    • Kushandura modhi kuita 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. Ndeipi nzira yemazuva ano, inoshandiswa mumasisitimu akaita seStable Diffusion 3, yakakura kubva mukuenderera kuyerera mazano?
    • Backpropagation kuburikidza nenguva
    • Kuyerera kuenzanirana (kudzidza ndima yekumhanya inotakura ruzha kune data)
    • Kukamura Mazwi
    • Beam search
  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