Maswali yanayounganishwa na mwongozo · Ngumu Kiwango

Maswali ya Kurekebisha Mitiririko

Tekeleza mabadiliko ya mtiririko unaoweza kugeuzwa, msongamano wa mabadiliko ya vigeu, na masahihisho ya Kijakobu, ikijumuisha vikomo vya ugunduzi wa ukiukaji kulingana na uwezekano.

Njia za mwongozo zinazohusianaMitiririko ya kawaida
Swali 1 ya 8

Ni mali gani ya kihesabu lazima kila mabadiliko katika mtiririko wa kawaida yawe nayo?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Ni mali gani ya kihesabu lazima kila mabadiliko katika mtiririko wa kawaida yawe nayo?
    • Lazima iwe ramani ya nasibu, isiyoweza kugeuzwa
    • Ni lazima iwe invertible (bijective) na tofauti
    • Ni lazima kupunguza dimensionality katika kila hatua
    • Lazima iwe jedwali bainifu la kuangalia
  2. Ni fomula gani huruhusu mtiririko wa kawaida kuhesabu uwezekano kamili?
    • Kazi ya softmax
    • Mlinganyo wa Bellman
    • Sheria ya Bayes inatumika kwa kumbukumbu
    • Fomula ya mabadiliko-ya-vigeu kwa kutumia kibainishi cha Jacobian
  3. Kwa nini usanifu wa mtiririko kama RealNVP na Glow hutumia tabaka za kuunganisha?
    • Ili kutengeneza pembe tatu ya Jacobian ili kibainishi chake ni rahisi kukokotoa
    • Ili kufanya mfano usibadilike
    • Ili kuondoa hitaji la usambazaji wa msingi
    • Ili kubadilisha mfano kuwa 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. Ni mbinu gani ya kisasa, inayotumiwa katika mifumo kama vile Usambazaji Imara wa 3, iliyotokana na mawazo ya mtiririko endelevu?
    • Uenezaji nyuma kupitia wakati
    • Ulinganishaji wa mtiririko (kujifunza sehemu ya kasi inayosafirisha kelele hadi data)
    • Uwekaji alama
    • Utafutaji wa boriti
  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