quiz bu lëkkale ak tegtal · Dëgër Niveau

Quiz ci model yu sukkandiko ci energie

Jëfandikool probabilite yu lalu ci energie, fonction xaaj, ak poñ gradient yi, boole ci ni energie relatif yi di doxee ratios séddale yu jaar yoon.

Yooni njiit yu jëm ciModèle yu sukkandiko ci energie
Laaj 1 de 8

Ci xeetu model bu sukkandiko ci energie, naka la energie di méngoo ak probabilite bu benn poñ de done?

Xoolaatal laaj bu nekk8 laaj

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

  1. Ci xeetu model bu sukkandiko ci energie, naka la energie di méngoo ak probabilite bu benn poñ de done?
    • Energie bu bari mooy probabilite bu bari
    • Energie bu néew dafay tekki ni am nga wërsëg (p(x) mingi méngoo ak exp(-E(x)))
    • Energy ak probabilite bokku ñu
    • Probabilite mingi méngoo ak energie bi ci saasi
  2. Lan moo tax tàggat model yu lalu ci energie jafe?
    • Fonction energie mënul nekk reso neuronal
    • Done yuñ etikete rek lañu soxla
    • Mënuñu wane nataal
    • Fonction partition Z (normaliseur ci kaw bépp dugg) dafay jafe xayma
  3. Ban xeetu jël misaal lañu gëna jëfandikoo ngir jël misaal ci EBM?
    • Dinamiku Langevin (MCMC bu lalu ci degrade)
    • Seetug limyéer
    • Tànneef bu gaaw
    • Benn paas ci kanam
  4. Lan moo waral pexe yu melni méngale poñ yi mënu ñu xayma fonction partition Z?
    • Ndax Z dafay tollu ci 1 saa yu nekk
    • Ndax duñu bàyyi xel ci fonction energie
    • Ndax degrade bu log p(x) mooy -degrade bu E(x), ak Z (konstant ci x) dafay wàcci suñuy wuutale
    • Ndax ci done yu wuute kese lañuy liggéey
  5. Ci yii, yan ci ñoom mooy xeetu energie bu yàgg bi?
    • Transformatër bi
    • Garab giy jël dogal
    • Algorithm biy tekki k
    • Reseau Hopfield
  6. For a differentiable EBM density with Z constant in x, how does its score relate to energy?
    • The score equals the partition function itself
    • The score equals the negative input gradient of energy
    • The score ignores the learned energy entirely
    • The score is always the positive energy gradient
  7. An EBM adds the same constant c to every E(x). What happens to normalized probabilities?
    • Every probability increases by c
    • All inputs become equally probable
    • They remain unchanged after the partition function is adjusted
    • The normalizer must be set to zero
  8. For two configurations with E(a) lower than E(b), what follows under the same normalized Gibbs model?
    • Configuration a has greater probability than b
    • Configuration b has greater probability because its energy is higher
    • Both probabilities must be exactly one
    • The comparison requires different partition functions for each point